Identifying the Defective: Detecting Damaged Grains for Cereal Appearance Inspection
arXiv:2311.11901 · doi:10.3233/FAIA230329
Abstract
Cereal grain plays a crucial role in the human diet as a major source of essential nutrients. Grain Appearance Inspection (GAI) serves as an essential process to determine grain quality and facilitate grain circulation and processing. However, GAI is routinely performed manually by inspectors with cumbersome procedures, which poses a significant bottleneck in smart agriculture. In this paper, we endeavor to develop an automated GAI system:AI4GrainInsp. By analyzing the distinctive characteristics of grain kernels, we formulate GAI as a ubiquitous problem: Anomaly Detection (AD), in which healthy and edible kernels are considered normal samples while damaged grains or unknown objects are regarded as anomalies. We further propose an AD model, called AD-GAI, which is trained using only normal samples yet can identify anomalies during inference. Moreover, we customize a prototype device for data acquisition and create a large-scale dataset including 220K high-quality images of wheat and maize kernels. Through extensive experiments, AD-GAI achieves considerable performance in comparison with advanced AD methods, and AI4GrainInsp has highly consistent performance compared to human experts and excels at inspection efficiency over 20x speedup. The dataset, code and models will be released at https://github.com/hellodfan/AI4GrainInsp.
arXiv commentAccepted by ECAI2023. https://github.com/hellodfan/AI4GrainInsp
References in corpus (25)
- Adam: A Method for Stochastic Optimization
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Distilling the Knowledge in a Neural Network
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- mixup: Beyond Empirical Risk Minimization
- Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
- CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
- Generalized Out-of-Distribution Detection: A Survey
- CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset
- Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
- DOTA: A Large-scale Dataset for Object Detection in Aerial Images
- Explainable Deep One-Class Classification
- CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
- Future Frame Prediction for Anomaly Detection -- A New Baseline
- OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
- DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection
- Anomaly Detection via Reverse Distillation from One-Class Embedding
- Everything You wanted to Know about Smart Agriculture
- Large Scale Visual Food Recognition
- SimpleNet: A Simple Network for Image Anomaly Detection and Localization
- Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food
- DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
- GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grains