Deep Convolutional Neural Network for Coffee Bean Inspection

Abstract

Coffee is one of the most popular drinks in the world. It contains antioxidants and healthpromoting nutrients that can boost one's energy and focus. However, defective beans mixed in with raw beans can easily affect the flavor and even be harmful to human health. The traditional human visual inspection of defective beans is extremely laborious and time-consuming and may result in low-quality coffee due to worker stress and fatigue. We propose a lightweight and explainable intelligent coffee bean quality inspection system that uses deep learning (DL) and computer vision (CV) technologies to assist operators in detecting defects, including mold, fermentation, insect bites, and crushed beans. We use knowledge distillation (KD) to achieve model compression. The basic explainable convolutional neural network (CNN) model is established using the explainable AI (XAI) method. The implemented system has a high identification rate, low complexity, and low power consumption, and can explain the judgment criteria of the complex classification model.

Computer Vision for Identifying and Classifying Green Coffee Beans: A Review

“…Wang et al proposed a system which could intelligently inspect coffee bean quality using deep learning and computer vision [27]. They used deep neural network (DNN), knowledge distillation (KD), and residual neural network (ResNet) to achieve their goals.…”

“…Wang et al [27] used saliency maps to segment important features of a coffee bean. Green spots in the saliency maps refer to the defective coffee bean parts, then the model computes the difference of pixel values in the images between defective and good coffee beans.…”

“…The local explainable model-agnostic explanation method (LIME) was used by Wang et al [27]. LIME classifies coffee beans by converting pixels with green colors into an explainable model by using the quality analysis of green beans produced by linear regression in the previous step.…”

Automatic Tariff Classification System using Deep Learning

“…The dataset was provided by Dubai Customs through an Artificial Intelligence (AI) hackathon competition held in October 2019. This data consisted of 22,346,194 records where each record had two attributes; the Harmonized System Code (HS-Code) and the description of the user inputs. The machine learning models applied were: Naïve Bayes, K-Nearest Neighbor, Decision Tree, Random Forest, Linear Support Vector Machine and Adaboost.…”

“…The trained CNN could classify approximately 13.77 coffee bean images per second with 98.19% accuracy of the classification. In [22], an intelligent coffee bean quality inspection system based on deep learning (DL) and computer vision (CV) was developed to assist operators in detecting defects, including mold, fermentation, insect bites, and crushed beans. An opensource dataset of coffee bean images was used for testing.…”