Automatic graph extraction from color images

Corner detection in color images through a multiscale combination of end-stopped cortical cells

The object contour detection in natural scenes is an important research problem in computer vision. The difficulty is that the integrity of contour extracted is interfered with a large number of texture edges in the background seriously. In recent years, some researchers have introduced image contour detection method with biological visual features and achieved preferable results. Such as, based on the fact of visual outer region suppression, they can suppress a certain amount of texture edge while extracting the contour of the object, and obtain the proper contour edge. However, when this method is used for contour detection in some image which the texture is similar to the contour, the texture edge still cannot be removed well, and the result is unsatisfactory. In consideration of the merit and demerit of the feature suppressed method, we propose an improved algorithm for object contour detection in natural scene based on image saliency. Firstly, the initial contour is obtained by using the suppression effect of non-classical receptive field, and the saliency map is obtained by using the hyper-complex Fourier transform image saliency detection method, and then the initial contour and the saliency map are integrated into the final contour. Compared with the traditional contour detection method, the contour extraction algorithm based on image saliency can remove more background information and improve the accuracy and integrity of object contour extracted in natural scenes.

In this paper we propose an image corner detector based on the direct curvature scale space (DCSS) technique, referred to as the curvature product DCSS (CP-DCSS) corner detector. After the contours of interested objects are extracted from a real-world image, their curvature functions are respectively convolved with the Gaussian function as its standard deviation gradually increases. By measuring the product of the curvature values computed at several given scales, true corners on the contours can be easily detected since false or insignificant corners have been effectively suppressed. A point is declared as a corner when the absolute value of the curvature product exceeds a given threshold and is a local maximum at the mentioned point. CP-DCSS combines the advantages of two recently proposed corner detectors, namely, the DCSS corner detector and the multi-scale curvature product (MSCP) corner detector. Compared to DCSS, CP-DCSS omits a parsing process of the DCSS map, and hence it has a simpler structure. Compared to MSCP, CP-DCSS works equally well, however, at less computational cost.

Local image feature extractors that select local maxima of the determinant of Hessian function have been shown to perform well and are widely used. This paper introduces the negative local minima of the determinant of Hessian function for local feature extraction. The properties and scale-space behaviour of these features are examined and found to be desirable for feature extraction. It is shown how this new feature type can be implemented along with the existing local maxima approach at negligible extra processing cost. Applications to affine covariant feature extraction and sub-pixel precise corner extraction are demonstrated. Experimental results indicate that the new corner detector is more robust to image blur and noise than existing methods. It is also accurate for a broader range of corner geometries. An affine covariant feature extractor is implemented by combining the minima of the determinant of Hessian with existing scale and shape adaptation methods. This extractor can be implemented along side the existing Hessian maxima extractor simply by finding both minima and maxima during the initial extraction stage. The minima features increase the number of correspondences by two to four fold. The additional minima features are very distinct from the maxima features in descriptor space and do not make the matching process more ambiguous.

Efficient local and global contour detection based on superpixels

Corner detection algorithm is an algorithm which helps in identifying the corners in an image. Corners are mainly formed by the combination of two or more edges. These corners may or may not define the boundary of an image. Here the method used is Harris corner detection algorithm. It helps in pointing out the corners in a color image, for each component. This improves the detection efficiency and the experimental results shows that this method is more reliable than traditional methods.

The complex hairiness of slub yarns makes it challenging to accurately detect the yarn body and measure its appearance parameters. This paper proposes a method for measuring the parameters of continuous slub yarn images based on computer vision. First, overlapping slub yarn sequence images are captured using a specially designed image capture device. Then, an image stitching method based on normalized cross-correlation is proposed to remove the overlapping data from neighboring slub yarn images. To handle the complex hairiness around the slub yarn, an improved knowledge-enhanced contour detection method is used to accurately extract the backbone contour of the slub yarn. Finally, the extracted slub yarn contour is analyzed using such methods as frequency histograms and curve fitting. Contour detection results show that the proposed yarn contour detection method achieves better performance, with an optimal dataset scale of 0.930 and an optimal image scale of 0.931. The parameters of slub yarn measured using the proposed method are consistent with the production process settings. The experimental results demonstrate that the method can accurately detect slub yarn parameters, providing a basis for the appearance design and proofing of slub fabrics in textile enterprises.

It is an important task to count the number of the objects in the image automatically. Because the objects in the image are sometimes overlapped with each other and even covered with different shaped objects, it is very difficult to detach these objects before counting them. Circular Hough transform has been used extensively to detect and count overlapped objects with circular shapes. However it can not detach the overlapping circular objects efficiently, and the counting task will provide inaccurate results when the circular objects are covered with random shaped objects. To deal with this problem, an integrated method is proposed based on the Hough Transform and Contour Detection methods. Furthermore, a software is implemented using the open source computer vision library Opencv 3.0 with visual studio 2012. The experimental results show that the proposed method can detach and count the objects accurately.

In clinical medicine, CT (Computerized Tomography) scanning is often carried out on parts of the human body with pathological changes, in order to diagnose and treat disease. When it is needed to establish a model of different parts for human body, related data of establishing model could be obtained through the scanned images. In this paper, the contour detection and extraction for CT images of knee joint are implemented through the designed VB (Visual Basic 6.0) program. The detective algorithms for contour include: first-order and second-order differential operators. The image processing effects of the differential operators with horizontal and vertical direction are better than operators with single direction. The chain code method is adopted for contour extraction, and pixels information on the image contour is saved. Through this designed program it provides the foundation for independent development of digital image processing program and from 3d medical images to the three dimensional geometric model building.

A New Straight Line Matching Technique by Integration of Vision-based Image Processing

We present a neural architecture that models the visual processing functionality of cortical cells. Taking into account intracortical processing, we analyze the properties of both simple and complex cells. For simple cells, a linear model is developed to derive their equivalent receptive fields. For complex cells, simulations are presented characterizing how they perform in texture discrimination.

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.

The paper presents a robust corner tracking method for unconstrained motions. The aim is to track corners in video sequences and identify best correspondences under any transformation, perspective distortion and intensity changes. To extract corners from each video frame, the multi-scale enhanced CSS (curvature scale space) corner detector is applied. In the matching stage, a new two-frame correspondence algorithm using multiple matches is employed. Experiments have been carried out on a wide range of real video sequences depicting translation, scaling, rotation and affine transformation, including non-smooth motions with different lighting and different camera motions. All the results were compared to the results of the popular Tommasini feature tracking algorithm (Tommasini, T. et al., IEEE Conf. on Computer Vision and Pattern Recognition, 1998). Experiments and comparison of the results confirm that the proposed corner tracker is more efficient, and more robust for unconstrained and non-smooth motions. These properties make it specially useful for video database retrieval and multimedia applications.

Corner detection and feature extraction are widely used in image processing and computer vision applications. In this paper, we propose a new gray-level corner detection based on virtual electric field model having different configurations, which demonstrate the best detection. The basic idea is to model the image as a grid of virtual electric charges of a plane surface in electrostatic balance. The algorithm is achieved in two main steps. The first one uses an adaptive method for computing directional gradients which permits to build an edge detection operator of 3times3 pixels. The second one introduces this operator for determining image derivatives in order to detect the corners. The smoothed squared images derivatives are given by using a Gaussian function. Then, the response function proposed by Harris and Stephens is computed for each pixel, using auto-correlation matrix. The local maxima search is performed as a final step of the method. Simulation results on synthetic and real images show the performances of the proposed method compared to that presented by an improved version of Harris detector.

The paper addresses the problem of corner tracking for multimedia applications in the presence of occlusion. To extract corners from each frame of a video sequence, multi-scale enhanced CSS (curvature scale space) corner detection is applied. In the matching stage, two-frame correspondence using multiple match hypotheses is considered. Due to occlusion, not only the corners of the first frame, but also all the corners that appear for the first time in each frame are tracked through the input sequence. To remember the path of corners when tracking, each corner has a record. The record for each tracked corner includes the numbers of the start and end frames during the tracking of these corners in a sequence. By tracking new corners, the corners of hidden moving objects appear again and are tracked after disocclusion. We apply the proposed method to a number of real video sequences. All experiments confirm that the proposed corner tracker performs more robustly and it is practical even when occlusion happens.