3D object recognition with a linear time‐varying system of overlay layers

Abstract

Object recognition is a challenging task in computer vision with numerous applications. The challenge is in selecting appropriate robust features with tolerable computing costs. Feature learning attempts to solve the feature extraction problem through a learning process using various samples of the objects. This research proposes a two-stage optimization framework to identify the structure of a first-order linear non-homogeneous difference equation which is a linear time-varying system of overlay layers (LtvoL) that construct an image. The first stage consists of the determination of a finite set of impulses, called overlay layers, by the application of a genetic algorithm. The second stage defines the coefficients of the corresponding difference equation derived from L 2 regularization. Classification of the test images is possible by a novel process exclusively designed for this model. Experiments on the Washington RGB-D dataset and ETH-80 show promising results which are comparable to those of state-of-the-art methods for RGB-D-based object recognition.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Residual Self-Calibration and Self-Attention Aggregation Network for Crop Disease Recognition

“…In recent years, deep learning techniques, especially convolutional neural networks (CNN) [13][14][15], are rapidly becoming the preferred method to overcome the above-mentioned challenges [16][17][18][19][20]. Due to the scale invariance of the convolutional neural network, the image problem it solves is not limited by the scale and shows outstanding ability in recognition and classification.…”

Automated model for identification on mastoid of temporal bone image

“…This stage aims to clean objects with some noise around the image area, where non-region of interest (non-ROI) objects that are connected to the image boundary need to be removed [48]. Furthermore, this result is carried out with an image overlay with the aim of focusing the object on a particular image by covering the main object and displaying object identification (OII) which is the main focus [49]. By using an image overlay on medical images, it is possible to know the exact anatomy and visualize the anatomy of the temporal bone, especially MACS, thus potentially increasing the surgeon's analysis in performing a series of more complex examination procedures.…”