Adaptive feature extraction method for capsule endoscopy images

Dingchang Wu, Yinghui Wang, Haomiao Ma, Lingyu Ai, Jinlong Yang, Shaojie Zhang, Wei Li · 2023

Read Adaptive feature extraction method for capsule endoscopy images by Dingchang Wu, Yinghui Wang, Haomiao Ma, Lingyu Ai, Jinlong Yang, Shaojie Zhang, Wei Li (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10710972.txt.

Description

Dingchang Wu and co-authors improve feature matching for capsule endoscopy in a 2023 paper. A capsule camera drifts through the gut taking pictures, and software must track the same spots across frames. A classic detector uses one fixed brightness threshold, which blurs the traits of these soft, low-contrast images. Their method sets the threshold on the fly for each image patch.

The detector builds an image pyramid and adapts thresholds layer by layer. A descriptor called FREAK then encodes each feature so stomach features stand apart better. A motion statistics step and a cleanup algorithm weed out bad matches. Against the best past method, their approach ran in about four fifths of the time. Its average matching score also rose by five percent in moving capsule tests.

Catalog record

CREATORDingchang Wu, Yinghui Wang, Haomiao Ma, Lingyu Ai, Jinlong Yang, Shaojie Zhang, Wei Li
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE42 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10710972

Browse the full library · About the Tower of Babel