دورية أكاديمية
Adaptive feature extraction method for capsule endoscopy images
العنوان: | Adaptive feature extraction method for capsule endoscopy images |
---|---|
المؤلفون: | Dingchang Wu, Yinghui Wang, Haomiao Ma, Lingyu Ai, Jinlong Yang, Shaojie Zhang, Wei Li |
المصدر: | Visual Computing for Industry, Biomedicine, and Art, Vol 6, Iss 1, Pp 1-13 (2023) |
بيانات النشر: | SpringerOpen, 2023. |
سنة النشر: | 2023 |
المجموعة: | LCC:Drawing. Design. Illustration LCC:Computer applications to medicine. Medical informatics LCC:Computer software |
مصطلحات موضوعية: | Capsule endoscopy, Feature extraction, Adaptive threshold, Drawing. Design. Illustration, NC1-1940, Computer applications to medicine. Medical informatics, R858-859.7, Computer software, QA76.75-76.765 |
الوصف: | Abstract The traditional feature-extraction method of oriented FAST and rotated BRIEF (ORB) detects image features based on a fixed threshold; however, ORB descriptors do not distinguish features well in capsule endoscopy images. Therefore, a new feature detector that uses a new method for setting thresholds, called the adaptive threshold FAST and FREAK in capsule endoscopy images (AFFCEI), is proposed. This method, first constructs an image pyramid and then calculates the thresholds of pixels based on the gray value contrast of all pixels in the local neighborhood of the image, to achieve adaptive image feature extraction in each layer of the pyramid. Subsequently, the features are expressed by the FREAK descriptor, which can enhance the discrimination of the features extracted from the stomach image. Finally, a refined matching is obtained by applying the grid-based motion statistics algorithm to the result of Hamming distance, whereby mismatches are rejected using the RANSAC algorithm. Compared with the ASIFT method, which previously had the best performance, the average running time of AFFCEI was 4/5 that of ASIFT, and the average matching score improved by 5% when tracking features in a moving capsule endoscope. |
نوع الوثيقة: | article |
وصف الملف: | electronic resource |
اللغة: | English |
تدمد: | 2524-4442 |
Relation: | https://doaj.org/toc/2524-4442 |
DOI: | 10.1186/s42492-023-00151-6 |
URL الوصول: | https://doaj.org/article/0540faeedd6648129169a239b35dc764 |
رقم الأكسشن: | edsdoj.0540faeedd6648129169a239b35dc764 |
قاعدة البيانات: | Directory of Open Access Journals |
تدمد: | 25244442 |
---|---|
DOI: | 10.1186/s42492-023-00151-6 |