A Review of methods for Textureless Object Recognition

TL;DR

This paper reviews various methods for recognizing textureless objects in computer vision, highlighting challenges, recent advances, and categorizing approaches into view-based, feature-based, and shape-based techniques.

Contribution

It provides a comprehensive overview of existing textureless object recognition methods, including recent deep learning approaches and a review of conference papers.

Findings

Deep learning enhances recognition accuracy

Shape-based methods are effective for textureless objects

Recent datasets like TLess have advanced research

Abstract

Textureless object recognition has become a significant task in Computer Vision with the advent of Robotics and its applications in manufacturing sector. It has been very challenging to get good performance because of its lack of discriminative features and reflectance properties. Hence, the approaches used for textured objects cannot be applied for textureless objects. A lot of work has been done in the last 20 years, especially in the recent 5 years after the TLess and other textureless dataset were introduced. In our research, we plan to combine image processing techniques (for feature enhancement) along with deep learning techniques (for object recognition). Here we present an overview of the various existing work in the field of textureless object recognition, which can be broadly classified into View-based, Feature-based and Shape-based. We have also added a review of few of the research papers submitted at the International Conference on Smart Multimedia, 2018. Index terms: Computer Vision, Textureless object detection, Textureless object recognition, Feature-based, Edge detection, Deep Learning