Development of an Optimal Algorithm for Detecting Damaged and Diseased Potato Tubers Moving along a Conveyor Belt Using Computer Vision Systems

Abstract

The article discusses the problem of detecting sick or mechanically damaged potatoes using machine learning methods. We proposed an algorithm and developed a system for the rapid detection of damaged tubers. The system can be installed on a conveyor belt in a vegetable store, and it consists of a laptop computer and an action camera, synchronized with a flashlight system. The algorithm consists of two phases. The first phase uses the Viola-Jones algorithm, applied to the filtered action camera image, so it aims to detect separate potato tubers on the conveyor belt. The second phase is the application of a method that we choose based on video capturing conditions. To isolate potatoes infected with certain types of diseases (dry rot, for example), we use the Scale Invariant Feature Transform (SIFT)—Support Vector Machine (SVM) method. In case of inconsistent or weak lighting, the histogram of oriented gradients (HOG)—Bag-of-Visual-Words (BOVW)—neural network (BPNN) method is used. Otherwise, Otsu’s threshold binarization—a convolutional neural network (CNN) method is used. The first phase’s result depends on the conveyor’s speed, the density of tubers on the conveyor, and the accuracy of the video system. With the optimal setting, the result reaches 97%. The second phase’s outcome depends on the method and varies from 80% to 97%. When evaluating the performance of the system, it was found that it allows to detect and classify up to 100 tubers in one second, which significantly exceeds the performance of most similar systems.

Promising real-time fruit and vegetable quality detection technologies applicable to manipulator picking process

“…Tan et al [23] Mandarin Surface defects ANN, RF 88.95% Hadimani et al [24] Texture, color, shape ANN-HS, ANN-ABC, KNN Sabzi et al [25] Tomato Color BPNN 99.31% Wan et al [26] Color SVM, KNN, ANN 97.78%-99.81% (SVM) 93.78%-99.32% (KNN) 91.33%-99.32% (ANN) de Luna et al [27] Potato Disease SIFT-SVM, HOG-BOVW-BPNN, CNN 97.00% Korchagin et al [28] Deep learning Cassava Disease MobileNetV2 97.70% Abayomi-Alli et al [29] Apple Surface lesion CycleGAN, DenseNet-YOLO v3 -Tian et al [30] Bruise CNN, SVM-VGG19, SVM-Inceptionv3 97.67% Hu et al [12] Tomato Surface defects ResNet50 91.70% da Costa et al [31] Banana Color, texture, and surface defects YOLO v3-SVM 96.40% Zhu et al [32] Papaya Color ResNet101, ResNet50, ResNet18, VGG19, VGG16, GoogleNet, AlexNet 100%(VGG19) Behera et al [33] Citrus Surface defects STA-CNN 98.00% Zhang et al [34] Note: a , Abbreviations: SVM, support vector machines;…”

Progress in the Application of CNN-Based Image Classification and Recognition in Whole Crop Growth Cycles

“…A lightweight model, CarrotNet, based on machine vision and DCNN was proposed to classify carrots [123]. Similar studies have also been conducted [118,[124][125][126][127][128].…”

Exploiting Pre-Trained Convolutional Neural Networks for the Detection of Nutrient Deficiencies in Hydroponic Basil

“…Meanwhile, studies have been carried out to develop different kinds of agricultural production techniques; to use fertilizers according to the result of the analysis of the elements in plants, soil and water; to perform irrigation according to the plant’s need for water [ 3 , 4 ]; to watch the weather conditions [ 5 , 6 ]; to detect plant pests (insects, weeds, etc.) [ 7 , 8 ] and to detect damage that has already occurred [ 9 , 10 ].…”