A Novel Cloning Template Designing Method by Using an Artificial Bee Colony Algorithm for Edge Detection of CNN Based Imaging Sensors

Abstract

Cellular Neural Networks (CNNs) have been widely used recently in applications such as edge detection, noise reduction and object detection, which are among the main computer imaging processes. They can also be realized as hardware based imaging sensors. The fact that hardware CNN models produce robust and effective results has attracted the attention of researchers using these structures within image sensors. Realization of desired CNN behavior such as edge detection can be achieved by correctly setting a cloning template without changing the structure of the CNN. To achieve different behaviors effectively, designing a cloning template is one of the most important research topics in this field. In this study, the edge detecting process that is used as a preliminary process for segmentation, identification and coding applications is conducted by using CNN structures. In order to design the cloning template of goal-oriented CNN architecture, an Artificial Bee Colony (ABC) algorithm which is inspired from the foraging behavior of honeybees is used and the performance analysis of ABC for this application is examined with multiple runs. The CNN template generated by the ABC algorithm is tested by using artificial and real test images. The results are subjectively and quantitatively compared with well-known classical edge detection methods, and other CNN based edge detector cloning templates available in the imaging literature. The results show that the proposed method is more successful than other methods.

Tuberculosis Diagnostics and Localization in Chest X-Rays via Deep Learning Models

“…Similarly, ResNet models implement average pooling at the very last pooling layer, whereas VGGNet and GoogLeNet Inception models use max pooling. Simply put, to boost the performance of different deep CNN models and better utilize their internal parameters, a unified modification for the part that lies between the main modules and the output of original CNN architectures is needed (Parmaksizoglu and Alçi, 2011 ).…”

“…In another study, Serizawa and Fujita ( 2020 ) have proposed linearly decreasing weight particle swarm optimization for hyperparameters optimization of CNN. Parmaksizoglu and Alçi ( 2011 ) have proposed using the ABC algorithm for parameter tuning in CNN based edge detection in images. ABC, a metaheuristic algorithm (Karaboga, 2005 ), was inspired by the foraging behavior of bees; it has been abstracted into a mathematical model to solve multidimensional optimization problems (Karaboga and Basturk, 2007 ).…”

GPNRBNN: A Robot Image Edge Detection Method Based on Gaussian Positive-Negative Radial Basis Neural Network

“…In the early stage, Paik [8] made use of the rotation invariance of the layered neural network to obtain the image edge. Selami [9] conducted edge detection and tracking in cancer cell tissue images through the multi-layer perceptor neural network with back propagation training algorithm. Khammari [10] used a convolutional neural network (CNN) with universal binary neurons to deal with the problem of edge detection on grayscale images.…”

Efficient Edge Detection by Adapting Artificial Bee Colony Algorithm

“…Authors claim ABC algorithm is a powerful optimisation technique, they compare their results against results obtained using genetic algorithms techniques. In Parmaksizoglu and Alci (2011), the edge detection process is performed using cellular neural networks (CNN). More specifically, the ABC algorithm was used to design the cloning template of a CNN.…”