Automatic threshold

Integral Imaging (InIm) is one of the most promising technologies for producing full color 3-D images with full parallax. InIm requires only one recording in obtaining 3D information and therefore no calibration is necessary to acquire depth values. The compactness of using InIm in depth measurement has been attracting attention as a novel depth extraction technique. In this paper, an algorithm for depth extraction that builds on previous work by the authors is presented. Three main problems in depth map estimation from InIm have been solved; i) the uncertainty and region homogeneity at image location where errors commonly appear in disparity process, ii) dissimilar displacements within the matching block around object borders, iii) object segmentation. This method is based on the distribution of the sample variance in sub-dividing non-overlapping blocks. A descriptor which is unique and distinctive for each feature on InIm has been achieved. Comparing to state-of-the-art techniques, it is shown that the proposed algorithm has improvements on two aspects: 1) depth map extraction level, 2) computational complexity.

Integral Imaging (InIm) is one of the most promising technologies for producing full color 3-D images with full parallax. InIm requires only one recording in obtaining 3D information and therefore no calibration is necessary to acquire depth values. The compactness of using InIm in depth measurement has been attracting attention as a novel depth extraction technique. In this paper, an algorithm for depth extraction that builds on previous work by the authors is presented. Three main problems in depth map estimation from InIm have been solved; i) the uncertainty and region homogeneity at image location where errors commonly appear in disparity process, ii) dissimilar displacements within the matching block around object borders, iii) object segmentation. This method is based on the distribution of the sample variance in sub-dividing non-overlapping blocks. A descriptor which is unique and distinctive for each feature on InIm has been achieved. Comparing to state-of-the-art techniques, it is shown that the proposed algorithm has improvements on two aspects: 1) depth map extraction level, 2) computational complexity.

Integral Imaging (InIm) is one of the most promising technologies for producing full color 3-D images with full parallax. InIm requires only one recording in obtaining 3D information and therefore no calibration is necessary to acquire depth values. The compactness of using InIm in depth measurement has been attracting attention as a novel depth extraction technique. In this paper, an algorithm for depth extraction that builds on previous work by the authors is presented. Three main problems in depth map estimation from InIm have been solved; i) the uncertainty and region homogeneity at image location where errors commonly appear in disparity process, ii) dissimilar displacements within the matching block around object borders, iii) object segmentation. This method is based on the distribution of the sample variance in sub-dividing non-overlapping blocks. A descriptor which is unique and distinctive for each feature on InIm has been achieved. Comparing to state-of-the-art techniques, it is shown that the proposed algorithm has improvements on two aspects: 1) depth map extraction level, 2) computational complexity.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

An improved pinch detection algorithm is proposed for low-cost antipinch window control systems. Apart from previous works, the proposed algorithm makes use of torque rate information to sense pinched conditions and to perform safety precautions. The motivation for this approach comes from the idea that the torque rate is less sensitive to motor parameter uncertainty than the torque or the angular velocity. The pinch estimator is designed by applying steady-state Kalman filter recursion to the augmented system model which includes the motor dynamics model and an additional torque rate state. The external torque rate is estimated using angular velocity measurements calculated from the Hall sensor output. A systematic way to set a reasonable threshold of the torque rate estimates under pinched conditions is suggested through deterministic estimation error analysis. Therefore, the proposed algorithm is able to prevent performance degradation due to the empirical threshold level as well as due to motor parameter variations. Experimental results show that our method satisfies EU legal requirements and guarantees robustness against parametric uncertainties.

Integral Imaging (InIm) is one of the most promising technologies for producing full color 3-D images with full parallax. InIm requires only one recording in obtaining 3D information and therefore no calibration is necessary to acquire depth values. The compactness of using InIm in depth measurement has been attracting attention as a novel depth extraction technique. In this paper, an algorithm for depth extraction that builds on previous work by the authors is presented. Three main problems in depth map estimation from InIm have been solved; i) the uncertainty and region homogeneity at image location where errors commonly appear in disparity process, ii) dissimilar displacements within the matching block around object borders, iii) object segmentation. This method is based on the distribution of the sample variance in subdividing non-overlapping blocks. A descriptor which is unique and distinctive for each feature on InIm has been achieved. Comparing to state-of-the-art techniques, it is shown that the proposed algorithm has improvements on two aspects: 1) depth map extraction level, 2) computational complexity.

Integral Imaging (InIm) is one of the most promising technologies for producing full color 3-D images with full parallax. InIm requires only one recording in obtaining 3D information and therefore no calibration is necessary to acquire depth values. The compactness of using InIm in depth measurement has been attracting attention as a novel depth extraction technique. In this paper, an algorithm for depth extraction that builds on previous work by the authors is presented. Three main problems in depth map estimation from InIm have been solved; i) the uncertainty and region homogeneity at image location where errors commonly appear in disparity process, ii) dissimilar displacements within the matching block around object borders, iii) object segmentation. This method is based on the distribution of the sample variance in subdividing non-overlapping blocks. A descriptor which is unique and distinctive for each feature on InIm has been achieved. Comparing to state-of-the-art techniques, it is shown that the proposed algorithm has improvements on two aspects: 1) depth map extraction level, 2) computational complexity.

Discovering patterns from large datasets is inevitable in the modern data driven civilization. Many research works, and business models are depending on this data excavation task. An efficient method for identifying and categorizing different data patterns from an exponentially growing database is required to perform a clear data excavation. A set of fresh processes such as Repeat Pattern Finder, Repeat Pattern Table, Repeat Pattern Threshold Analyzer, and Repeat Pattern Node are conceptualized in this work named as Auto-Threshold Dynamic Memory Efficient Frequent Pattern Growth for Data Excavation (AT-DME-FP). The main motive of this work is to improve the Accuracy, Precision, Recall, and F-Score along with the decrease in time and memory consumption.  AT-DME-FP is contrived in a way to reduce the consumption of computational resources to match the modern data mining outgrowth. The memory reduction ability of AT-DME-FP makes it possible to use it with big data seamlessly.

Integral Imaging (InIm) is one of the most promising technologies for producing full color 3-D images with full parallax. InIm requires only one recording in obtaining 3D information and therefore no calibration is necessary to acquire depth values. The compactness of using InIm in depth measurement has been attracting attention as a novel depth extraction technique. In this paper, an algorithm for depth extraction that builds on previous work by the authors is presented. Three main problems in depth map estimation from InIm have been solved; i) the uncertainty and region homogeneity at image location where errors commonly appear in disparity process, ii) dissimilar displacements within the matching block around object borders, iii) object segmentation. This method is based on the distribution of the sample variance in subdividing non-overlapping blocks. A descriptor which is unique and distinctive for each feature on InIm has been achieved. Comparing to state-of-the-art techniques, it is shown that the proposed algorithm has improvements on two aspects: 1) depth map extraction level, 2) computational complexity.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

Segmentation of medical images is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region have similar intensity. In this paper, we introduce a new automatic method for region growing capable to segment 2D/3D Magnetic Resonance Images (MRI) and Computed Tomography (CT) which contain weak boundaries between different tissues. The proposed method is used to extract reliable regions of an image to produce a computer aided design for 3D images. It includes an automatic threshold and is based on estimating probability of pixel intensities of a given image. An automatic threshold is computed as a function of intensity and probability of pixels. This makes the threshold to be flexible and can give large threshold when pixels have very similar intensities and small when they are on the boundaries. The experimental results show that the proposed technique produces accurate and stable results.

In this paper, the automotive power window has been integrated with an advanced safety mechanism called anti-pinch system for good protection. Based on a contact method, a new safety mechanism using a low-cost technology has been proposed to set a threshold value as a limit to decide the pinch condition, or automatic threshold method. The electric current information is easily detected by using current sensor installed on a motor driver without incorporating extra device. Then the pinch condition is quickly reflected and calculated by using current information in the system. Since the automatic threshold is decided by analyzing system behavior in advance, the optimal calculation can be guaranteed and then applied it on the safety mechanism in a cost-effective manner. Through extensive experimental tests, the squeezing forces of the proposed anti-pinch system have been verified to satisfy requirements of the FMVSS 118 regulations.