Applied Mechanics and Materials Vols. 321-324

Abstract: The imaging detector of the nuclear radiation is applied widely in radiation detection, the safety monitor and nuclear medical imaging. We aimed to make scientific researches on nuclear radiant source through the pinhole imaging system .The imaging system was designed that base on the Imarad 16×16 pixel-array CdZnTe semiconductor detector. The detector has high sensitivity to low energy under 200kev at room temperature. We applied the detector and pinhole system to obtain the image of the radiant source that the energy was up 200kev.The detection efficiencies of 38.92 mm×38.92 mm by 5 mm thick CdZnTe pixel-array detector were measured. The capability of the whole system was test and evaluated. The rough image of the radiant source was achieved through the test. When the location of the source and pinhole parameter were changed, the image would vary correspondingly. The accurate image could acquired by means of image reconstruction .So it is feasible that the research about the localization and qualification of the nuclear radiation is making use of the pinhole system.

Abstract: Region of interest (ROI) play important roles in image analysis and processing areas. In order to solve the problems of large scale storage and transmission of ID photos, this paper presents an approach to extract the ROI of ID photos. A standard facial training database is established by these extracted images. PCA algorithm extracts facial feature values of the extracted images and applied them to facial recognition. Facial recognition algorithm is efficient to manage these ID photos.

Abstract: Traffic signs effected by shooting environment and natural environment , and varying degrees of geometric distortion. This work introduced a new method to extract the traffic signs' Hu moment features that based on affine invariant. First , according to the shape coordinates x,y of traffic sign is independent of each other before affine transformation . Then getting traffic signs only have rotating effect by ICA transformation . Finally , recognizing traffic sign by compare the Hu's moment feature. Results show this method can greatly improve the feature extraction accuracy of Hu moments and traffic sign recognition efficiency

Abstract: The developing economy and convenience of traffic makes the building more and more large, and the traffic is also increasing quickly. The light pollution caused by glass curtain walls in high-rise building makes the traffic safety problems more and more serious. Enough attention should be paid towards it. A simulation software was written in order to make a graphic simulation of the sun's running status, analysis of various types of architectural glass curtain wall and building orientation on light pollution regional distribution effect. It's summed up that the use of decumbent form glass curtain wall can be effective in controlling light pollution area size and can reduce the glare range by properly reversing buildings, in order to avoid light pollution’s influence on traffic safety.

Abstract: Bag of words algorithm is an efficient object recognition algorithm based on semantic features extraction and expression. It learns the virtues of the text-based search algorithm to make images a range of visual words, extract the semantic characters and carry out the detection and recognition of interesting objects. Bag of words algorithm is extracted from gray images and discard s color information of images. We propose in this paper a method of image retrieval based on clustered domain colors and bag of words algorithm. The results of experiments show that this method can improve the precision of retrieval efficiently.

Abstract: Wireless video surveillance is of increasing importance. Many wireless video surveillance systems require a well optimized video codec for low-power operations. Compression of the captured video is normally needed in order to reduce the amount of video data to be delivered as well as to increase the video storage capability of the surveillance system. In this paper, a method which can greatly reduce the complexity for one of the most time-consuming parts in a video encoder was proposed.

Abstract: As a unique combination of science and art, digital art is impacting on the traditional art form. Digital art is actively connected with popular culture and consuming culture by the use of television, computer, Internet and other means. Digital art also has a strong influence on public culture which is successfully avoided the defects such as personal privacy and narrow sense. Digital art is an art form which is built on some certain technology conditions. However, the artistic rules of digital art works should not be less than the technical rules. After all, artists should avoid changing and covering the shallow performance of the art concept by using the digital form of technology.

Abstract: To reduce the high memory cost of fast retireval method, we present a fast retrieval method based on bucket map chain on the basis of Exact Euclidean Locality Sensitive Hashing (E2LSH). The bucket map chain contains all the points projected from feature space in multiple buckets, which store the nearby points. When conducting query, it searches the chain by the bucket index of query point and locates the position of related buckets, then reads the related points in related buckets and measurs the similarity of these points with query point. The experiments show that this method can efficiently decrease the memory cost of retrieval. It is very important for increasing the feasibility of large scale information retrieval especially image retrieval.

Abstract: With the development of the Virtual Reality technology and the next Human-Machine Interaction technology, this paper focus on the object motion detection and object skin color analysis, provide one kind of hand gesture segmentation method based on one camera. This method capture the image from the single camera to detect the moving object by the time difference method and the Gaussian module method, tracking the hand motion region real time, then to segment the hand gesture using the specified region skin color features after the hand region is extracted. Using the motion detection and the skin color features both, to do static gesture recognition by the template match method after extracting the features of the static gesture contour.This experiment make clear that the segmentation has better effect and recognition result.

Abstract: Mechanical engineering is a discipline of engineering that applies the principles of physics and materials science for analysis, design, manufacturing, and maintenance of mechanical systems. It is the branch of engineering that involves the production and usage of heat and mechanical power for the design, production, and operation of machines and tools. It is one of the oldest and broadest engineering disciplines. The notion of orthogonal vector-valued binary wavelet packs is introduced. Their traits is investigated by virtue of time-frequency analysis method and finite group theory. Orthogonality formulas are established. Orthonormal wavelet pack bases are obtained. A novel method for constructing a kind of orthogonal shortly supported vector-valued wavelets is presented.