Image stitching and image reconstruction of intestines captured using radial imaging capsule endoscope

Abstract

This study investigates image processing using the radial imaging capsule endoscope (RICE) system. First, an experimental environment is established in which a simulated object has a shape that is similar to a cylinder, such that a triaxial platform can be used to push the RICE into the sample and capture radial images. Then four algorithms (mean absolute error, mean square error, Pearson correlation coefficient, and deformation processing) are used to stitch the images together. The Pearson correlation coefficient method is the most effective algorithm because it yields the highest peak signal-to-noise ratio, higher than 80.69 compared to the original image. Furthermore, a living animal experiment is carried out. Finally, the Pearson correlation coefficient method and vector deformation processing are used to stitch the images that were captured in the living animal experiment. This method is very attractive because unlike the other methods, in which two lenses are required to reconstruct the geometrical image, RICE uses only one lens and one mirror.

Color calibration of swine gastrointestinal tract images acquired by radial imaging capsule endoscope

“…The RICE images were warped images, and unwrapped images can be obtained using the conversion equation for converting polar coordinates into Cartesian coordinates. 13 Before color correction, we considered to stitch all the images or to correct every color image before stitching images. If all the images were to be multiplied by the transformation matrix for color correction, the corrected color images would be slightly different from the original color images, which would result in minor errors during image registration.…”

“…Recently, the optical design of RICE including imaging and illumination systems has been achieved, 11,12 and image registration and connection studies on gastrointestinal images captured during various times in animal experiments have been conducted in previous study. 13 However, the color images have not been color corrected, causing distortion in the color information of color images. Thus, this study endeavored to address this problem, using color-correction algorithms to correct images and employing the International Commission on Illusion Delta E 2000 (CIEDE2000) color difference formula to compare the images before and after color correction.…”

Stitching and Surface Reconstruction From Endoscopic Image Sequences: A Review of Applications and Methods

“…The panorama was generated from circles extracted around the image center during constant pullback motion of the endoscope. Ou-Yang et al [113] (2012) stitched images from a radial imaging capsule endoscope (RICE) system by applying a similar unwrapping technique. Recently, Yi et al [169] (2013) have presented a real-time capsule endoscopy (CE) video visualization technique, based on unwrapped panorama images of the gastrointestinal (GI) tract.…”

Monocular stereo imaging using bi-slit projections from Forward motion video

“…The forward motion video, captured from the camera moving forward, which is a main mode of access to the scene in many applications such as environment surveillance, endoscopy, pipeline inspection and mobile navigation [1,2,3] . 3D information constructed from forward motion video can facilitate the applications due to the strong sense of reality and wealth of information.…”