Affiliations: [a]
Shenzhen Institute of Information Technology, Shenzhen, China
| [b] Rehabilitation Department of Traditional Chinese Medicine, Dazhou Central Hospital, Sichuan, China
Correspondence:
[*]
Corresponding author. Miao He, Rehabilitation Department of Traditional Chinese Medicine, Dazhou Central Hospital, Sichuan, China. E-mail: [email protected].
Abstract: With the establishment and development of technologies and theories such as computer technology, image processing, pattern recognition and artificial intelligence, image analysis systems have gradually become one of the methods of automatic quantitative analysis and testing in the medical field. However, the current technology is limited to the objectivity and comprehensiveness of blood edge detection, and no detection method with high accuracy can be found. In order to accurately and effectively detect the blood color of the color ultrasound image, this paper classifies the image feature extraction method, and simulates the classical differential algorithm, mathematical morphology algorithm and fuzzy Pal.King. In the following, the classical canny algorithm and its improved algorithm and the improved fuzzy Pal.King algorithm are introduced in detail. Finally, the simulation results are obtained. Among the indicators tested, DD has the highest accuracy. In the curve analysis, the FI value of FIB was > 0.05, the area under the curve of FDP was 67.9%, the sensitivity was 64%, and the specificity was 59%. In this paper, the quantitative analysis of the image feature extraction effect is given by the calculation results, and the subjective and objective unity is achieved. At the same time, the improved algorithm proposed in this paper is applied to the evaluation system for analysis and summary, and the results obtained are consistent with the theoretical analysis.
