Showing papers by "Heng-Da Cheng published in 2007"

Computerized-aid diagnosis of breast mass using ultrasound image.

Abstract: This paper presents a comparative study of the diagnostic results of the ultrasologists with/without using a novel enhancement algorithm for breast ultrasonic images based on fuzzy entropy principle and textural information. Totally, 350 ultrasound images of 115 cases were analyzed including 59 benign and 56 malignant lesions. The original breast images were fuzzified, the edge and textural information were extracted, and the images were enhanced. The original and enhanced images were assessed and evaluated by ultrasologists using double blind method before and after enhancement. The diagnostic sensitivity and specificity were calculated by the areas (Az) under the receiver operating characteristic (ROC) curves. And the two diagnostic results before and after enhancement were compared by Chi-square test in a 2 x 2 table. The results demonstrated that the discrimination rate of breast masses had been highly improved after employing the novel enhancement algorithm. The result indicates the sensitivity could be raised from 74.3% to 89.3% with the false-positive rate 14.3%, and the area (Az) under the ROC curve of diagnosis also increased from 0.84 to 0.93. The novel enhancement algorithm can increase the classification accuracy and decrease the rate of missing and misdiagnosis, and it is useful for breast cancer control.

Novel contrast enhancement approach based on fuzzy homogeneity

Abstract: Contrast enhancement is an important issue in image processing, pattern recognition, and computer vision. There are two major kinds of techniques for contrast enhancement: indirect methods and direct methods. The indirect approach is to modify the histogram by changing the original gray levels to new values; it is not efficient and effective because it only stretches the global distribution of the intensities. The basic idea of the direct method is to define a measurement of the contrast and use it to enhance the contrast. Fuzzy logic has been widely applied to image processing since fuzzy set theory can handle the uncertainly, vagueness, and imprecision inherent in the images well. The proposed approach employs the fuzzy entropy principle and fuzzy set theory to automatically determine fuzzy membership functions and uses fuzzy homogeneity to define the contrast and enhance the image. We have conducted experiments on a variety of images, and the results have proved that the proposed method has better performance than the existing approaches.

Novel Airborne Real-Time Survey System

Abstract: Although satellite imaging is widely used today, an airborne survey system is still more efficient and effective under certain circumstances. Airborne survey can successfully detect and transmit target information in real time that is useful and critical for related agencies, such as environmental management, natural-disaster monitor and control, etc. Using a real-time synthetic-aperture-radar image processing approach based on a distribution system, image data are synchronized with a global positioning system; a satellite-communication system of data transmission is designed and implemented; and a novel image-compression method, which is wavelet-based, is developed. The main idea of the proposed system is based on a function-distribution personal computer (PC) system: Data preprocessing, post processing, and extraction of images, data processing, image display, and image printing, are performed by different PCs. The method of image transmission proposed here is based on the satellite communication system. The proposed system has the advantage of low cost (both hardware prototype and maintenance) and rapid processing speed (only in several seconds; the disaster images from the air are processed and transmitted to the Disaster Reduction Center and to other users by the satellite communication system). The system has been applied to a real-time disaster monitor (such as a forest fire, a flood, etc.), real-time target tracking, large-scale topographic mapping, environmental survey, etc.

Contrast enhancement using texture histogram and fuzzy entropy

Abstract: Image enhancement is used to correct contrast deficiencies and to improve the quality of an image. It is essential and critical to extracting features and segmenting images. This paper presents a novel contrast enhancement algorithm based on newly defined texture histogram and fuzzy entropy with the ability to preserve edges and details, while avoiding noise amplification and over-enhancement. To demonstrate the performance, the proposed algorithm is tested on a variety of images and compared with other enhancement algorithms. Experimental results proved that the proposed method has better performance in enhancing images without over-enhancement and under-enhancement.