| Summary: | 碩士 === 國立臺灣大學 === 電信工程學研究所 === 94 === Research of image segmentation has been studied for many years. Image segmentation techniques are important but difficult in many image processing topics, such as object recognition and content-based image retrieval. In order to solve those problems, a successful image segmentation method is essential for splitting an image into meaningful regions, such as the discrimination between foreground and background of the segmentation of moving object and constant background. Then, make again these fundamental units (such as pixels or blocks) into further significant processing.
In Part A, the task of Segmentation in video sequence based on DCT domain is dividing the video sequence into frames, and dividing 8X8 pixels element block each frame. Then passes through a continually string to calculate after determining this block is belongs to the foreground or the background. The main framework is to transfer each 8X8 block into 2 dimension-DCT domain in order to get the information of frequency domain, and then utilize the relation in the identical position block to calculate the threshold of background and foreground. This method has the quite good performance of catching moving object and also show to be low sensitive to illumination change and to noise.
---------
With the growing technique of communication between human and robot, the problem of human face recognition has attached more importance and become the current research in the popular domain of computer vision and recognition model. Thus, human’s skin color is always an important mechanism and principle basis of human face detection. Human’s skin color has the relative stability with the difference of the majority background object appearance. The skin color does not rely on the face detail characteristic and do not change with the face expression and rotation. Therefore, utilizing skin color to examine human face in color image is an important context of human face recognition.
In Part B, we provide a fast algorithm to identify human race with face skin color. The basic construction is roughly dividing human race into three parts: white, yellow and black race, then using Gaussian Mixture Model to train the feature parameter of each human race with large number of training images. Afterward, utilize Bayesian Decision Rule to determine the human race of test images.
|
|---|
