Feature Recalibration Based Olfactory-Visual Multimodal Model for Fine-Grained Rice Deterioration Detection

Dimensions overall score 9.0

GitHub Code Pulse

No public code linked for this paper yet.

• The proposed feature recalibration based olfactory-visual multimodal model achieves a classification accuracy of 99.89% for rice deterioration detection.result 95%
• The Fine-grained Deterioration Embedding Constructor (FDEC) reconstructs labeled multimodal embedded-feature datasets to enhance sample representation.method 85%
• The Fine-grained Deterioration Recalibration Attention Network (FDRA-Net) emphasizes signal variations and increases sensitivity to fine-grained deterioration on the rice surface.method 85%
• The proposed method simplifies the rice deterioration detection procedure compared to state-of-the-art methods.result 80%
• The proposed method improves detection accuracy compared to state-of-the-art methods.result 90%
• The proposed method can be extended to other agrifood applications in the agriculture and food industry.technical 75%
• The method relies on specific hardware (camera and e-nose), which might limit versatility.limitation 70%
• The proposed olfactory-visual multimodal model achieves a classification accuracy of 99.89% for fine-grained rice deterioration detection.result 70%
• The fine-grained deterioration embedding constructor (FDEC) is proposed to reconstruct labeled multimodal embedded-feature datasets, enhancing sample representation.method 70%
• The fine-grained deterioration recalibration attention network (FDRA-Net) is proposed to increase sensitivity to fine-grained deterioration on the rice surface.method 70%
• The proposed method simplifies the detection procedure compared to state-of-the-art methods.technical 70%
• The proposed method can be extended to other agrifood applications in the agriculture and food industry.market 70%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card