Colour Imaging

The objective of this project is the development of an algorithm for the automatic recognition of traffic signs in digital images. The program An.Si. was created (from the Greek words Anagnorisi Simaton which means Sign Recognition). Up to now, many algorithms for the traffic sign detection and classification have been introduced. Extensive research is being made by major car manufacturing companies in collaboration with Universities and other institutes on real-time and automatic recognition of traffic signs, so that it can be a part of the so called "Driver Support Systems" ([7]). Two major problems exist in the whole detection process. Road signs are frequently occluded partially by other vehicles. Many objects are present in traffic scenes which make the sign detection hard (pedestrians, other vehicles, buildings and billboards may confuse the detection system by patterns similar to that of road signs). Colour information from traffic scene images is affected by varying illumination caused by weather conditions, time (daynight) and shadowing (buildings) ([7]). The proposed method detects the location of the sign in the image, based on its geometrical characteristics and recognises it using colour information. Partial occlusion is dealt by the use of the Hough Transform and suggestions are made for future improvements so that the robustness of the algorithm in light condition changes can be increased.

Several colour descriptors are presented each year. The existing protocols to evaluate and compare these descriptors are restricted to the use of image databases without information about the spatio-chromatic content. In this article, we present a first answer to calibrate a colour texture descriptor. By calibration, we intend evaluate the capacity of the descriptor to discriminate the non-uniform aspect according to different scales of samples. In order to assess all the possibilities in term of spatial frequencies and colour content, we propose to use reference images based on a fractal vector colour model. Three texture features are compared from this protocol allowing to express the interest of the proposed calibration sequence.

Face detection is a image processing technology that determines the location and size of human faces in digital images or video. This module precedes face recognition systems that plays an important role in applications such as video surveillance, human computer interaction and so on. This proposed work focuses mainly on multiple face detection technique, taking into account the variations in digital images or video such as face pose, appearances and illumination. The work is based on skin color model in YCbCr and HSV color space. First stage of this proposed method is to develop a skin color model and then applying the skin color segmentation in order to specify all skin regions in an image. Secondly, a template matching is done to assure that the segmented image does not contain any non-facial part. This algorithm works to be robust and efficient.

Arthur Jafa (Tupelo, Mississippi, 1960), winner of the Golden Lion at
the 2019 Venice Art Biennale, is an African-American artist and filmmaker, who has contributed to the global affirmation of a black audiovisual
aesthetic based on the body and its sonic extensions. In particular, the artist
identifies the specificity of black culture in what he defines as Black Visual
Intonation, by constructing the audiovisual phrasing on the temporality
of Afro-American music, which configures new possibilities for a black
aesthetics based on the sounding body. Starting from these premises, the
essay analyzes Love is the Message, the Message is Death (2016), which
intersects the modes of the essay film with those of music video, where the
black visual intonation works as a kinesthetic principle of emotional revival
that supports the audio-tactile continuity (Iannotta, 2017) between the film
and the spectator’s body.

Automatic vehicle type recognition (make and model) is very useful in secure access and traffic monitoring applications. It compliments the number plate recognition systems by providing a higher level of security against fraudulent use of number plates in traffic crimes. In this paper we present a simple but powerful probabilistic framework for vehicle type recognition that requires just a single representative car image in the database to recognize any incoming test image exhibiting strong appearance variations, as expected in outdoor image capture e.g. illumination, scale etc. We propose to use a new feature description, local energy based shape histogram 'LESH', in this problem that encodes the underlying shape and is invariant to illumination and other appearance variations such as scale, perspective distortions and color. Our method achieves high accuracy (above 94 %) as compared to the state of the art previous approaches on a standard benchmark car dataset. It provides a posterior over possible vehicle type matches which is especially attractive and very useful in practical traffic monitoring and/or surveillance video search (for a specific vehicle type) applications.

Automatic vehicle type recognition (make and model) is very useful in secure access and traffic monitoring applications. It compliments the number plate recognition systems by providing a higher level of security against fraudulent use of number plates in traffic crimes. In this paper we present a simple but powerful probabilistic framework for vehicle type recognition that requires just a single representative car image in the database to recognize any incoming test image exhibiting strong appearance variations, as expected in outdoor image capture e.g. illumination, scale etc. We propose to use a new feature description, local energy based shape histogram 'LESH', in this problem that encodes the underlying shape and is invariant to illumination and other appearance variations such as scale, perspective distortions and color. Our method achieves high accuracy (above 94 %) as compared to the state of the art previous approaches on a standard benchmark car dataset. It provides a posterior over possible vehicle type matches which is especially attractive and very useful in practical traffic monitoring and/or surveillance video search (for a specific vehicle type) applications.

Texture discrimination was the second more important task studied after colour perception and characterization. Nevertheless, few works explore the colour extension of these works and none for vectorial processing of this important visual information. In this work we propose a novel and vector processing for colour texture characterization, the color contrast occurrence matrix C 2 O. This new texture feature is based on the colour difference assessment. To be link to the human perception, the colour difference is expressed using a perceptual distance expressed in CIELab and two angles characterizing the chromaticity and darker or lighter direction. Through this new attribute, we analyze the stability to changes in illumination, viewpoint and spectrum of the light source in front of different texture image databases. Thanks to our construction, we avoid the main limit of existing texture features requiring an initial colour quantization or a binarization inside the texture construction. Keeping the small local contrast, we obtain a more accurate texture feature description explaining the obtained results. Then we carry out the construction of a features vector by occurrence quantization, keeping the initial ideas of Julesz, Haralick and Ojala, for the classification purposes. The results show best correct classification percentages in databases that with important spatio-chromatic complexity as ALOT.

La tesi riguarda il processo evolutivo dell’industria cinematografica italiana dal momento della sua prima espansione (biennio1906-1908) fino allo scoppio della I guerra mondiale. In particolare il lavoro si e concentrato sulle vicende societarie e produttive di una delle maggiori case di produzioni attive in Italia nel periodo preso in esame: la Milano Films. Le ricerche relative alla societa milanese hanno portato al rinvenimento di una cospicua quantita di documenti finora inediti, attraverso i quali e stato possibile ricostruire nel dettaglio la vicenda societaria e produttiva della casa di produzione. Lo studio ha inoltre analizzato le peculiarita specifiche che, tra il 1908 e il 1914, contraddistinguono la cinematografia italiana dal punto di vista degli assetti societari e finanziari, dell’organizzazione produttiva, delle strategie distributive e commerciali, attraverso un costante confronto con il complessivo quadro industriale italiano coevo e, in particolare, con quei sett...

This paper presents a new approach to segment and recognise traffic signs via two vision models: the colour appearance model CIECAM97s and Behaviour Model of Vision (BMV). This approach not only takes CIECAM97s into practical application for the first time since it was standardised in 1998, but also improves the accuracy of recognition of traffic signs dramatically, taking into account of changing weather conditions and varying transformations of signs. BMV model has been further developed to a foveal system for traffic signs (FOSTS). Comparison with the other colour spaces in terms of segmentation, including CIELUV and HSI, and RGB colour space is also carried out. The results show that CIECAM97s outperforms over the other three spaces with 94%, 90% and 85% accurate rate for sunny, cloudy and rainy viewing conditions respectively. It also confirms that CIECAM97s does predict the colour appearance similar to the average observer. For recognition stage, FOSTS system gives accuracy rates up to 95%.

This paper describes an efficient approach towards road sign detection and recognition. The proposed system is divided into three sections namely; Colour Segmentation of the road traffic signs using the HSV colour space considering varying lighting conditions, Shape Classification using the Contourlet Transform considering occlusion and rotation of the candidate signs and the Recognition of the road traffic signs using features of a Local Energy based Shape Histogram (LESH). We have provided experimental results and a detailed analysis to justify that the algorithm described in this paper is robust enough to detect and recognize road signs under varying weather, occlusion, rotation and scaling conditions.

Élisabeth Thuillier is best known by film historians for having colored Georges Méliès's films and films produced by Pathé. In his overview essay on "French Film Colorists" written for this publication, Joshua Yumibe notes that Méliès "outsourced his hand-coloring work from 1897 to 1912 to a Vincennes firm in Paris run by Elisabeth Thuillier who managed a workforce of over 200 female colorists. Her daughter Marie-Berthe Thuillier, known as Berthe Thuillier, probably worked with Élisabeth and then took over the workshop after her death in either 1904 or 1907.

This paper presents a new approach for color detection and segmentation based on Support Vector Machine (SVM) to retrieve candidate regions of traffic signs in real-time video processing. Instead of processing on each pixel, this approach utilizes a block of pixels as an input vector of SVM for color classification, where the dimension of each vector can be extended by a group of neighboring pixels. This helps to handle the diversification of data on both training and testing samples. After that, Hough transform and contour detection are applied to verify the candidate regions by detecting shapes of circle and triangle. The experimental results are highly accurate and robust for our testing database, where samples are recorded on various states of environment.

This paper presents a new approach for color detection and segmentation based on Support Vector Machine (SVM) to retrieve candidate regions of traffic signs in real-time video processing. Instead of processing on each pixel, this approach utilizes a block of pixels as an input vector of SVM for color classification, where the dimension of each vector can be extended by a group of neighboring pixels. This helps to handle the diversification of data on both training and testing samples. After that, Hough transform and contour detection are applied to verify the candidate regions by detecting shapes of circle and triangle. The experimental results are highly accurate and robust for our testing database, where samples are recorded on various states of environment.

Texture discrimination was the second more important task studied after colour perception and characterization. Nevertheless, few works explore the colour extension of these works and none for vectorial processing of this important visual information. In this work we propose a novel and vector processing for colour texture characterization, the color contrast occurrence matrix C 2 O. This new texture feature is based on the colour difference assessment. To be link to the human perception, the colour difference is expressed using a perceptual distance expressed in CIELab and two angles characterizing the chromaticity and darker or lighter direction. Through this new attribute, we analyze the stability to changes in illumination, viewpoint and spectrum of the light source in front of different texture image databases. Thanks to our construction, we avoid the main limit of existing texture features requiring an initial colour quantization or a binarization inside the texture construction. Keeping the small local contrast, we obtain a more accurate texture feature description explaining the obtained results. Then we carry out the construction of a features vector by occurrence quantization, keeping the initial ideas of Julesz, Haralick and Ojala, for the classification purposes. The results show best correct classification percentages in databases that with important spatio-chromatic complexity as ALOT.

This paper presents a new approach for color detection and segmentation based on Support Vector Machine (SVM) to retrieve candidate regions of traffic signs in real-time video processing. Instead of processing on each pixel, this approach utilizes a block of pixels as an input vector of SVM for color classification, where the dimension of each vector can be extended by a group of neighboring pixels. This helps to handle the diversification of data on both training and testing samples. After that, Hough transform and contour detection are applied to verify the candidate regions by detecting shapes of circle and triangle. The experimental results are highly accurate and robust for our testing database, where samples are recorded on various states of environment.

Texture discrimination was the second more important task studied after colour perception and characterization. Nevertheless, few works explore the colour extension of these works and none for vectorial processing of this important visual information. In this work we propose a novel and vector processing for colour texture characterization, the color contrast occurrence matrix C 2 O. This new texture feature is based on the colour difference assessment. To be link to the human perception, the colour difference is expressed using a perceptual distance expressed in CIELab and two angles characterizing the chromaticity and darker or lighter direction. Through this new attribute, we analyze the stability to changes in illumination, viewpoint and spectrum of the light source in front of different texture image databases. Thanks to our construction, we avoid the main limit of existing texture features requiring an initial colour quantization or a binarization inside the texture construction. Keeping the small local contrast, we obtain a more accurate texture feature description explaining the obtained results. Then we carry out the construction of a features vector by occurrence quantization, keeping the initial ideas of Julesz, Haralick and Ojala, for the classification purposes. The results show best correct classification percentages in databases that with important spatio-chromatic complexity as ALOT.

Macro x-ray fluorescence (XRF) imaging of cultural heritage objects, while a popular non-invasive technique for providing elemental distribution maps, is a slow acquisition process in acquiring high signal-to-noise ratio XRF volumes. Typically on the order of tenths of a second per pixel, a raster scanning probe counts the number of photons at different energies emitted by the object under x-ray illumination. In an effort to reduce the scan times without sacrificing elemental map and XRF volume quality, we propose using dictionary learning with a Poisson noise model as well as a color image-based prior to restore noisy, rapidly acquired XRF data.

Purpose: The main goal of this research is to introduce an approach of student modeling in a WEB based platform for learning games composing. Methods: As a theoretical background of the proposed model is used a didactical model of learning game, developed by the authors. The student model is evolved as a composition of sets, formally representing all the elements of the process of acquiring knowledge using a learning game Results: The general concept and a schematic notation of the proposed student model is presented and a detailed description is also given. The model consists of three areas reflecting activities, individualities and knowledge of the students: Interaction area, Archetype area and Competence area. The model's context is formed by a stimulus environment, for as much as it represents a student who is motivated to learn while playing a game. Conclusions: The proposed student model is intended to serve not only a standalone learning game but also a WEB-based platform for learning games composing.

A large class of real-world problems, arising in the administrative - organizational systems is connected with the attestation of the academic staff in accordance with predefined and linguistically described evaluation criteria. Such problems are solved in the circumstances of uncertainties of different types. The process of interpretation goes together with some ambiguity and inaccuracy due to the subjective interpretation of the criteria by experts. The Fuzzy Set theory provides a convenient apparatus for formalization and creation of new intelligent decision-making methods, based on analysis and processing of the expert knowledge. This paper offers a method of fuzzy modelling of the problem of scientific and pedagogical staff attestation which gives the possibility of an adequate interpretation of the attestation results. The method can be implemented programmatically and can be incorporated in the systems of education quality management.

Bank merupakan salah satu perusahaan yang memiliki aktivitas di dalamnya, tanpa adanya sebuah sistem yang memadai untuk menjalankan proses bisnis, tentunya akan mengurangi efektifitasnya. SDB (save deposit box) merupakan salah satu layanan yang di dalamnya terdapat beberapa proses bisnis, disamping itu SDB merupakan layanan tambahan yang diberikan kepada nasabah prioritas di bank. Salah satu bank yang menyadiakan layanan SDB adalah Bank Mandiri, namun sayangnya layanan SDB ini masih dikerjakan secara manual. Oleh karena itu diperlukannya sebuah sistem yang terkomputerisasi yang dapat membantu proses bisnis. Dengan menggunakan metode RUP (rational unified process) dan metode pengujian product metric akan menghasilkan sebuah sistem yang berkualitas baik dan sesuai dengan kebutuhan konsumen. Dengan adanya sistem ini dapat meningkatkan efektifitas dari proses bisnis yang berjalan. Kata kunci : SDB (save deposit box), RUP (rational unified process), product metric, metric

The aim of this paper is to obtain a new investigation technique on field of recognition and classification of traffic signs through artificial vision. The method consists of analyzing distances from edges of the shape to reference axis. The traffic sign classification is arranged by a Support Vectors Machine (SVM) which has been trained for circular, rectangular, triangular and octagonal forms. The process consists of two major steps: segmentation according to the color and identifying the geometric shape of the candidate blobs using SVMs. Before pattern recognition it is convenient to discard the blobs whose size is not properly. The most important advantages are its robustness against possible inclinations would have the traffic or highway sings, and on the other hand, its low computation load.

Texture discrimination was the second more important task studied after colour perception and characterization. Nevertheless, few works explore the colour extension of these works and none for vectorial processing of this important visual information. In this work we propose a novel and vector processing for colour texture characterization, the color contrast occurrence matrix C 2 O. This new texture feature is based on the colour difference assessment. To be link to the human perception, the colour difference is expressed using a perceptual distance expressed in CIELab and two angles characterizing the chromaticity and darker or lighter direction. Through this new attribute, we analyze the stability to changes in illumination, viewpoint and spectrum of the light source in front of different texture image databases. Thanks to our construction, we avoid the main limit of existing texture features requiring an initial colour quantization or a binarization inside the texture construction. Keeping the small local contrast, we obtain a more accurate texture feature description explaining the obtained results. Then we carry out the construction of a features vector by occurrence quantization, keeping the initial ideas of Julesz, Haralick and Ojala, for the classification purposes. The results show best correct classification percentages in databases that with important spatio-chromatic complexity as ALOT.

Face detection is a image processing technology that determines the location and size of human faces in digital images or video. This module precedes face recognition systems that plays an important role in applications such as video surveillance, human computer interaction and so on. This proposed work focuses mainly on multiple face detection technique, taking into account the variations in digital images or video such as face pose, appearances and illumination. The work is based on skin color model in YCbCr and HSV color space. First stage of this proposed method is to develop a skin color model and then applying the skin color segmentation in order to specify all skin regions in an image. Secondly, a template matching is done to assure that the segmented image does not contain any non-facial part. This algorithm works to be robust and efficient.

This paper presents a new approach for color detection and segmentation based on Support Vector Machine (SVM) to retrieve candidate regions of traffic signs in real-time video processing. Instead of processing on each pixel, this approach utilizes a block of pixels as an input vector of SVM for color classification, where the dimension of each vector can be extended by a group of neighboring pixels. This helps to handle the diversification of data on both training and testing samples. After that, Hough transform and contour detection are applied to verify the candidate regions by detecting shapes of circle and triangle. The experimental results are highly accurate and robust for our testing database, where samples are recorded on various states of environment.

Since Google Street View (GSV) services provide volumetric street view panoramas with associated geo-referenced information, this research aims to explore useful information from GSV streamlines. This research aims on developing an internet platform that integrates Google Maps API, HTML5 and JavaScript routines for accessing the GSV panoramas and associated orientation parameters in order to identify traffic signs and to determine their georeferenced positions. Being under development using OpenCV, OpenMP and C++, various techniques in detecting, extracting, recognizing, and positioning of traffic signs from cropped GSV streamlines along user-selected routes are primarily concerned for low-cost, volumetric and quick establishment of infrastructural database in public transportation networks towards value-added Location-Based Services.

Road sign plays an important role in highway system management by providing drivers and road users guidance, warning and other driving related information. Proper sign maintenance and inventory is therefore necessary. Sign inventory system is an essential tool for infrastructure management and maintenance. Currently, sign inventory is mostly conducted by human observation of the digital images of roadway scenes. Automated system would substantially improve the processing speed and accuracy of two key processing tasks, sign detection and sign classification, since the human observation of the large amount of images is tedious, error-prone and time-consuming. The research in this final report emphasizes on the study of the classification. Classification is to categorize signs into proper classes, which is important and also more difficult for automation in the automated sign inventory system. The most frequently used technique in previous research for classification is neural network. However, neural network has the local minimum problem. In addition, neural network lacks explainable inner theoretical rule which brings difficulty to fine tune the performance of the model. This research presents a method for sign classification which combines feature extraction, Support Vector Machine (SVM), and multi-class classification. SVM is a statistical learning method based on Vapnik-Chervonenkis (VC) dimension and structural minimum principle. It is supposed to overcome the aforementioned two drawbacks of neural network method. The feature extraction is accomplished by Principal Component Analysis (PCA) which reduces the dimension of the image as well as keeping the most important features. Preliminary experimental result presented in the report demonstrates that the SVM method has potential to solve the road sign classification problem.

In this paper Streetlight object identification is addressed using the notion of image processing. An approach based on Image Processing Techniques is proposed for selection and processing of features from the images. Histogram and Region was applied on the extracted images. Histogram and Region features were then extracted and employed to train the Support Vector Machine (SVM) classifier for streetlight recognition. Experimental results shows 99.1%, 84% and 100% for histogram, region features and combination of both respectively. Experimental results have proved that the proposed method is robust, accurate, and powerful in object recognition.

The robust identification of the traffic signs represents the first and one of the most important steps in the development of a traffic sign recognition (TSR) system. Traffic signs detection usually involves a color segmentation process that uses the information related to the chromatic properties of the road signs. Since the traffic video data is captured in diverse road and weather conditions, the problem relating to traffic sign detection is quite challenging. Among several issues that need to be addressed during this processing stage, the problem generated by mutually occluding traffic signs (mutual occlusion occurs when one traffic sign partially occludes the surface of other road signs) that are attached to the same pole require special attention. In these situations the color segmentation process fails to correctly identify the regions that are associated with the traffic signs. These traffic sign detection failures compromise the performance of other stages of the TSR system and in this paper we propose two approaches that address the segmentation of mutually occluding traffic signs. The first approach uses the information associated with the inner parts of the traffic signs, while the second approach applies the watershed transform to identify the signs that have their borders in contact or are mutually occluding.

In this paper Streetlight object identification is addressed using the notion of image processing. An approach based on Image Processing Techniques is proposed for selection and processing of features from the images. Histogram and Region was applied on the extracted images. Histogram and Region features were then extracted and employed to train the Support Vector Machine (SVM) classifier for streetlight recognition. Experimental results shows 99.1%, 84% and 100% for histogram, region features and combination of both respectively. Experimental results have proved that the proposed method is robust, accurate, and powerful in object recognition.

An adaptive technique for color image segmentation is presented in this paper. The segmentation is performed using a multiresolution scheme and considering the background areas have quite uniform color features at a low-resolution representation of the image. ...

In this paper, we present a novel approach for the detection and recognition of traffic signs. Colour images are acquired by a camera mounted in a car. In the first step, these images are colour segmented with a pixel classifier. Colour combinations which are characteristic for traffic signs generate hypotheses. These hypotheses are verified using a pictogram classifier. Our system has been successfully tested on thousands of traffic scenes. The processing of a 512 by 512 frame takes approximately 1 second on a Spare-10. This project is part of the European research programme PROMETHEUS and is being developed by Daimler-Benz in collaboration with various university labs.

In this paper a complete automatic system for roadsign detection, tracking, and classification is presented and evaluated. The processing of video frames in the L*a*b color space improves significantly the sign detection rate by processing the same frame in different normalized color spaces. The tracking module reduces significantly the processing time by transferring the sign detection information in the next frames and processing different radii signs in parallel. The proposed system is evaluated in normal, raining and night driving conditions. In a total number of 266 roadsign recordings, the complete system track and recognize successfully 216. The main source of system fault appears in city night driving due to the presence of a great number of light sources.

To give sheltered and symphonies stream of movement , particular standards are given by each administration. There are certain rules laid down by the government of most of the countries for the safe, systematic and orderly movement of vehicles and traffic. Many of these rules are displayed through traffic signs to help the driver to follow while driving. The Traffic Sign Detection and Recognition (TSDR) perceives the activity signs by dissecting pictures /recordings taken from a camera system and helps in detecting and recognizing the traffic signs by analyzing images / videos captured by the camera planted on the car. This framework has many elements which help the driver in enhancing the well being and solace; today it is broadly utilized as a part of discovery and acknowledgement of our perceived signs. The framework of system can be developed using two algorithms, first is the detection of the image followed by its recognition. In wake of getting the best possible information fo...

This paper presents the implementation of an automatic road sign recognizer for an intelligent transport system. In this system, lists of road signs are processed with actions such as line segmentation, single sign segmentation, and storing an artificial sign in the database. The process of taking the video stream and extracting the road sign and storing in the database is called the road sign recognition. This paper presents a study on recognizing traffic sign patterns using a segmentation technique for the efficiency and the speed of the system. The image is converted from one scale to another scale such as RGB to grayscale or grayscale to binary. The images are pre-processed with several image processing techniques, such as threshold techniques, Gaussian filters, Canny edge detection, and the contour technique.

This paper presents a new approach for color detection and segmentation based on Support Vector Machine (SVM) to retrieve candidate regions of traffic signs in real-time video processing. Instead of processing on each pixel, this approach utilizes a block of pixels as an input vector of SVM for color classification, where the dimension of each vector can be extended by a group of neighboring pixels. This helps to handle the diversification of data on both training and testing samples. After that, Hough transform and contour detection are applied to verify the candidate regions by detecting shapes of circle and triangle. The experimental results are highly accurate and robust for our testing database, where samples are recorded on various states of environment.

Traffic road sign detection is important to a robotic vehicle that automatically drives on roads. As the colors of most traffic road signs are blue and red, in this paper, we use Hue- Saturation- Intensity (HSI) color space for color based segmentation at first. Using important geometrical features, the road signs are detected perfectly. After segmentation, it turns to classify every detected road signs. For this purpose, we employ and compare the performance of three classifiers; they are distance to border (DTB), FFT sample of signature, and code matrix. In this work, we use the code matrix as an efficient classifier for the first time. Although the achieved accuracy by code matrix is greater than the two referred classifiers in average, the main advantage is simplicity and so less computational cost.

Traffic road sign detection is important to a robotic vehicle that automatically drives on roads. As the colors of most traffic road signs are blue and red, in this paper, we use Hue-Saturation-Intensity (HSI) color space for color based segmentation at first. Using important geometrical features, the road signs are detected perfectly. After segmentation, it turns to classify every detected road signs. For this purpose, we employ and compare the performance of three classifiers; they are distance to border (DTB), FFT sample of signature, and code matrix. In this work, we use the code matrix as an efficient classifier for the first time. Although the achieved accuracy by code matrix is greater than the two referred classifiers in average, the main advantage is simplicity and so less computational cost.

Traffic sign classification system is a part of driving assistance system that automatically alerts and instructs the driver about the meaning of traffic signs. In this paper, we proposed the idea for classifying automatically each type of traffic signs. The proposed method has been tested with a publicly available dataset: German Traffic Sign Recognition Benchmark (GTSRB). We use 360 images for testing by grouping traffic signs into 12 groups and images are taken by short distance from camera. In the first stage of our method, we have to separate particular traffic sign from background using color analysis, edge detection, and region of interest (ROI). In the process of ROI, we use Hough Transform algorithm to detect the different shapes of circle, square, and triangle. After we obtained edge images and images from ROI, in the subsequent stage we use 75% of images for training and 25% of images for testing using support vector machine classification algorithm. From ROI image we use feature extraction to get normal direction from edge image and also use support vector machine (SVM) to classify and compare results between ROI and ROI with normal direction feature. In our experimental results, using ROI and SVM can improve the efficiency of classification which has the accuracy 73%, ROI with normal direction feature and SVM can improve the efficiency of classification which has the accuracy 88.60%, when compare with the original involved background 67.80%. The improvement from SVM is about 5% and 20.8% respectively.

Automatic detection of road sign is a challenging but demanding job. A new approach namely automatic detection and recognition of traffic signs (ADRTS) considering color segmentation, moment invariants, and neural networks has been proposed in this paper. Experimental result proves the superior performance in the detection and recognition of road signs. Computational time complexity is also quite low that makes it applicable for the real time system. Index Terms-traffic sign, automation, neural network, moment invariants, hu moment.

Automatic detection of road sign is a challenging but demanding job. A new approach namely automatic detection and recognition of traffic signs (ADRTS) considering color segmentation, moment invariants, and neural networks has been proposed in this paper. Experimental result proves the superior performance in the detection and recognition of road signs. Computational time complexity is also quite low that makes it applicable for the real time system. Index Terms-traffic sign, automation, neural network, moment invariants, hu moment.

Automatic detection of road sign is a challenging but demanding job. A new approach namely automatic detection and recognition of traffic signs (ADRTS) considering color segmentation, moment invariants, and neural networks has been proposed in this paper. Experimental result proves the superior performance in the detection and recognition of road signs. Computational time complexity is also quite low that makes it applicable for the real time system. Index Terms-traffic sign, automation, neural network, moment invariants, hu moment.

Traffic road sign detection is important to a robotic vehicle that automatically drives on roads. As the colors of most traffic road signs are blue and red, in this paper, we use Hue-Saturation-Intensity (HSI) color space for color based segmentation at first. Using important geometrical features, the road signs are detected perfectly. After segmentation, it turns to classify every detected road signs. For this purpose, we employ and compare the performance of three classifiers; they are distance to border (DTB), FFT sample of signature, and code matrix. In this work, we use the code matrix as an efficient classifier for the first time. Although the achieved accuracy by code matrix is greater than the two referred classifiers in average, the main advantage is simplicity and so less computational cost.