Narrow Results

We describe an object recognition system based on symbolic contour graphs. The image to be analyzed is transformed into a graph with object corners as vertices and connecting contours as edges. Image corners are determined using a robust multiscale corner detector. Edges are constructed by line-following between corners based on evidence from the multiscale Gabor wavelet transform. Model matching is done by finding subgraph isomorphisms in the image graph. The complexity of the algorithm is reduced by labeling vertices and edges, whereby the choice of labels also makes the recognition system invariant under translation, rotation and scaling. We provide experimental evidence and theoretical arguments that the matching complexity is below O(#V³), and show that the system is competitive with other graph-based matching systems.

During the production, transportation and storage of nonwoven fabric mask, there are many damages caused by human or nonhuman factors. Therefore, checking the defects of nonwoven fabric mask in a timely manner to ensure the reliability and integrity, which plays a positive role in the safe use of nonwoven fabric mask. At present, the wide application of machine vision technology provides a technical mean for the defect detection of nonwoven fabric mask. On the basis of the pre-treatment of the defect images, it can effectively simulate the contour fluctuation grading and gray value change of the defect images, which is helpful to realize the segmentation, classification and recognition of nonwoven fabric mask defect features. First, in order to accurately obtain the image information of the nonwoven fabric mask, the binocular vision calibration method of the defect detection system is discussed. On this basis, the defect detection mechanism of the nonwoven fabric mask is analyzed, and the model of image processing based on spatial domain and Hough transform is established, respectively. The original image of the nonwoven fabric mask is processed by region processing and edge extraction. Second, the defect detection algorithm of nonwoven fabric mask is established and the detection process is designed. Finally, a fast defect detection system for nonwoven fabric mask is designed, and the effectiveness of the detection method for nonwoven fabric mask is analyzed with an example. The results show that this detection method has positive engineering significance for improving the detection efficiency of defects in nonwoven fabric mask.

In infrared image and recognition processing, the target edge is an important feature and plays a crucial role. According to the properties of infrared image we have made a key research in double filtration and functions of “highlighting frames and reinforcing contrast” in lateral inhibition network, and put forward an image edge detection-based method. The method has some restraint over noise and evident effect in edge detection. In light of sequence images’ relevance we have utilized immune algorithm to segment object’s moving areas and form object templates. Then we have obtained the updated templates in the state of moving sequence frames and finally low-contrast, low-noise and edge-blurred sequence rims of infrared object images. The effect is good.

According to the feature of Buddha’s head light and backlight area is circle in Thangka image, so a method is proposed for detection of circle head light and backlight. Firstly, a method of morphology in edge extraction to get image edge is used, and by removing the edge connection point to get edge segment image. Secondly, through least square circle detection and verification condition of target circle to get the precise position of circle head light and backlight in Thangka image. The experimental results show that the method is with high accuracy and accurate positioning features in the detection of Buddha’s circle head light and backlight in Thangka Image.

Classical edge extraction is difficult for these images with the interference of non-distribute objects and uneven lighting. A new edge extraction approach combining Canny algorithm and Butterworth high-pass filter is proposed. Butterworth high-pass filter highlights objects and removes the background and some interference information in ore image. After histogram specification enhancing the contrast, Canny algorithm extracts accurate edges in these processed images. The experiments show that the result of new edge extraction method for complex ore images is more excellent than that of single Canny algorithm, it not only retains more closed edge, but also remove the noise and false edge.