Vision-Based Detection and Classification of Used Electronic Parts

Abstract

Economic and environmental sustainability is becoming increasingly important in today’s world. Electronic waste (e-waste) is on the rise and options to reuse parts should be explored. Hence, this paper presents the development of vision-based methods for the detection and classification of used electronics parts. In particular, the problem of classifying commonly used and relatively expensive electronic project parts such as capacitors, potentiometers, and voltage regulator ICs is investigated. A multiple object workspace scenario with an overhead camera is investigated. A customized object detection algorithm determines regions of interest and extracts data for classification. Three classification methods are explored: (a) shallow neural networks (SNNs), (b) support vector machines (SVMs), and (c) deep learning with convolutional neural networks (CNNs). All three methods utilize 30 × 30-pixel grayscale image inputs. Shallow neural networks achieved the lowest overall accuracy of 85.6%. The SVM implementation produced its best results using a cubic kernel and principal component analysis (PCA) with 20 features. An overall accuracy of 95.2% was achieved with this setting. The deep learning CNN model has three convolution layers, two pooling layers, one fully connected layer, softmax, and a classification layer. The convolution layer filter size was set to four and adjusting the number of filters produced little variation in accuracy. An overall accuracy of 98.1% was achieved with the CNN model.

Harnessing Deep Learning for Sustainable E-Waste Management and Environmental Health Protection

“…We used a number of evaluation criteria, including accuracy, precision, recall, F1-score, and confusion matrix to evaluate the effectiveness of our model for classifying e-waste (Chand & Lal, 2022) The model's capacity to correctly identify each class and strike a balance between precision and recall is illustrated as well by these metrics, which also offer insights into the total classi cation accuracy (Malik et al, 2022) For further understanding of the model's performance, we present the confusion matrix, Testing the Model…”

Preprocessing and improving image quality for identifying elements simple shape in machine vision system to automated industrial machines

“…It demonstrates high learning speed and object detection accuracy. In [7] explores an alternative method based on SVM and CNN to improve classification using low-resolution grayscale images. This requires less processing power (CPU and memory usage), but reduces accuracy.…”

Computational Models That Use a Quantitative Structure–Activity Relationship Approach Based on Deep Learning

“…A CNN is a type of deep-learning system that specializes in image recognition. After repeating the combination of the "convolution layer" and "pooling layer" multiple times, it finally outputs the result through a connected layer [44,45]. "Convolution" is an imageprocessing technique that extracts image features through a filter or kernel.…”