Woo-Beom Lee

Self-organization neural network for multiple texture image segmentation

Texture analysis is an important technique in many image processing areas, such as scene segmentation, object recognition, and shape and depth perception. But no efficient methods captures all aspects of the very diverse texture family including natural scenes. We propose a novel approach for efficient texture image analysis that use unsupervised learning schemes for the texture recognition task. The self-organization neural network for texture image identification is based on features that is extracted at angle and magnitude in the orientation-field that might be different from the sample textures. In order to show the performance of the proposed system, we have attempted to build various texture images. The experimental results show that the performance of the system is very successful.

Texture segmentation by unsupervised learning and histogram analysis using boundary tracing

Texture analysis is an important technique in many image processing areas, such as scene segmentation, object recognition, and shape&depth perception. However, most methods are restricted to issue of computational complexity and supervised problems. Accordingly, we propose a efficient method of segmenting texture that uses unsupervised learning schemes to discover a texture cluster without a pre-knowledge. This method applies 2D Gaussian filters to the clustered region iteratively, and the thresholding value for segmenting is automatically determined by analyzing histogram of the clustered inner-region. It can be acquired by the boundary tracing in the clustered region. In order to show the performance of the proposed method, we have attempted to build a various texture images, and the segmenting quality was measured according to the goodness based on the segmented shape of region. Our experimental results showed that the performance of the proposed method is very successful.

An adjacent multiple pedestrians detection based on ART2 neural network

This paper presents a method to detect adjacent multiple pedestrians using the ART2 neural network from a moving camera image. A BMA(Block Matching Algorithm) is used to obtain a motion vector from two consecutive input frames. And a frame difference image is generated by the motion compensation with the motion vector. This image is transformed into binary image by the adapted threshold and a noise is also removed. To detect multiple pedestrians, a projection histogram is processed by the shape information of human being. However, in case that pedestrians exist adjacently each other, it is very different to separate them. So, we detect adjacent multiple pedestrians using the ART2 neural network. The experimental results on our test sequences will show the high efficiency of our method.

Unsupervised approach for extracting the textural region of interest from real image

Neural network is an important technique in many image understanding areas. Then the performance of neural network depends on the separative degree among the input vector extracted from an original image. However, most methods are not enough to understand the contents of a image. Accordingly, we propose a efficient method of extracting a spatial feature from a real image, and segmenting the TROI (: Textural Region Of Interest) from the clustered image without a pre-knowledge. Our approach presents the 2-passing k-means algorithm for extracting a spatial feature from image, and uses the unsupervised learning scheme for the block-based image clustering. Also, a segmentation of the clustered TROI is achieved by tuning 2D Gabor filter to the spatial frequency the clustered region. In order to evaluate the performance of the proposed method, the segmenting quality was measured according to the goodness based on the segmented shape of region. Our experimental results showed that the performance of the proposed method is very successful.

Illusory surface perception using a hierarchical neural network model of the visual pathways

Illusory contours occurring in the various perceptual phenomena are essentially accompanied with illusory surfaces. Accordingly, we propose a novel approach for the perception of illusory surface arising from illusory contours. The proposed method uses a hierarchical neural network model. It is likely done in the visual cortex domain in a cascade manner, and uses the response properties of neuron cells found in the visual pathways. The stimuli for forming the illusory contours are induced by modelling the end-stopped cell, and the induced stimuli for the surface perception is then formed from the extracted illusory contours. Finally, the surface perception is completed by restoring surface successively from the induced contour stimuli. The proposed model was demonstrated on a variety of illusory contour figures, and experimental results showed that the perception of illusory surface is a very successful.

Multiple Texture Objects Extraction with Self-organizing Optimal Gabor-filter

The Optimal filter yielding optimal texture feature separation is a most effective technique for extracting the texture objects from multiple textures images. But, most optimal filter design approaches are restricted to the issue of supervised problems. No full-unsupervised method is based on the recognition of texture objects in image. We propose a novel approach that uses unsupervised learning schemes for efficient texture image analysis, and the band-pass feature of Gabor-filter is used for the optimal filter design. In our approach, the self-organizing neural network for multiple texture image identification is based on block-based clustering. The optimal frequency of Gabor-filter is turned to the optimal frequency of the distinct texture in frequency domain by analyzing the spatial frequency. In order to show the performance of the designed filters, after we have attempted to build a various texture images. The texture objects extraction is achieved by using the designed Gabor-filter. Our experimental results show that the performance of the system is very successful.

Traffic Sign Area Detection by using Color Rate and Distance Rate

This paper proposes a system detecting the area of traffic sign, which uses color rate as the information of colors, and corner point and distance rate as the information of morphology. In this system, a candidate area is extracted by performing dilation operation on the binary image made by the color rate of R, G, B components and by detecting corner point and center point through mask. The area of traffic sign with varied shapes is extracted by calculating the distance rate from center point, which is the information of morphology. The results of this experiment demonstrate that in this system which is invariable regardless of its size and location, it is possible to extract the exact area from varied traffic signs such as the shapes of triangle, circle, inverse triangle, and square as well as from the images at both day and night when brightness value is greatly different. Moreover, it demonstrates great accuracy and speed in processing.