A5003198124- Smart Agriculture and AI
- Spectroscopy and Chemometric Analyses
- Advanced Chemical Sensor Technologies
- Neural Networks and Applications
- Image Retrieval and Classification Techniques
- Water Quality Monitoring Technologies
- Advanced Image and Video Retrieval Techniques
- Remote Sensing and Land Use
- CCD and CMOS Imaging Sensors
- Spectroscopy Techniques in Biomedical and Chemical Research
- Identification and Quantification in Food
- Industrial Vision Systems and Defect Detection
- Plant Virus Research Studies
- Advanced Algorithms and Applications
- Peanut Plant Research Studies
- Visual Attention and Saliency Detection
- Marine animal studies overview
- Remote Sensing in Agriculture
- Image Processing Techniques and Applications
- Ichthyology and Marine Biology
- Genetics and Plant Breeding
- Genomics and Phylogenetic Studies
- Olfactory and Sensory Function Studies
- Digital Imaging for Blood Diseases
- Sparse and Compressive Sensing Techniques
Qingdao Agricultural University
2015-2025
China University of Petroleum, Beijing
2015-2018
China University of Petroleum, East China
2015-2018
Sino Biological (China)
2014
Plant pests mainly refers to insects and mites that harm crops products. There are a wide variety of plant pests, with distribution, fast reproduction large quantity, which directly causes serious losses crops. Therefore, pest recognition is very important for grow healthily, this in turn affects crop yields quality. At present, it great challenge realize accurate reliable identification.In study, we put forward diagnostic system based on transfer learning detection recognition. This method...
Freshness is the most critical indicator for fruit quality, and directly impacts consumers' physical health their desire to buy. Also, it an essential factor of price in market. Therefore, urgent study evaluation method freshness. Taking banana as example, this study, we analyzed freshness changing process using transfer learning established relationship between storage dates. Features images were automatically extracted GoogLeNet model, then classified by classifier module. The results show...
The motion trajectory of sea cucumbers reflects the behavior cucumbers, and status feeding individual health, which provides important information for culture, detection early disease warning. Different from traditional manual observation sensor-based automatic methods, this paper proposes a detection, location analysis approach based on Faster R-CNN under deep learning framework. designed system consists RGB camera to collect cucumbers' images corresponding cucumber identification software....
Abstract In order to screen high-quality peanut pod varieties on food processing production lines and promote the sustainable development of as well expansion its consumer market, this study improved recognition ability efficiency deep feature extraction by optimizing ResNet50 learning network model. Experimental results showed that accuracy optimized model reached 91.6%, which was 2.1% higher than original Additionally, extracted features appearance morphology pods, used agglomerative...
The number of soybean pods is a key determinant yield, making accurate detection and counting essential for yield estimation, cultivation management, variety selection. Traditional manual methods are labor-intensive time-consuming, while object networks widely applied in agricultural tasks, the dense distribution overlapping occlusion present significant challenges. This study developed pod model, YOLOv8n-POD, based on YOLOv8n network, incorporating innovations to address these issues. A...
<abstract> <b><i>Abstract. </i></b> Carrot grading is a labor intensive, time-consuming process and usually performed manually in practical manufacturing. Manual inspection poses many problems maintaining consistency guaranteeing the detection efficiency. To improve efficiency achieve automatic detection, we developed an automated carrot sorting system using machine vision technology. The consisted of image processing system, acquisition roller conveying control system. It first picked out...
Abstract It is extremely important to correctly identify the carrot appearance quality in design and manufacturing of Carrot sorter. In this paper, we have established a control system based on deep learning framework. The information collected using image, thereafter recognition model erect AlexNet network, which pre‐trained by large‐scale computer vision database (Image‐Net). Our framework uses transfer learning, trains neural networks with small amounts data compared traditional CNN....
To investigate the feasibility of identification qualified and adulterated oil product using hyperspectral imaging(HIS) technique, a novel feature set based on quantized histogram matrix (QHM) selection method improved kernel independent component analysis (iKICA) is proposed for HSI. We use UV Halogen excitations in this study. Region interest(ROI) images 256 samples from four varieties are obtained within spectral region 400-720nm. Radiation indexes extracted each ROI used as vectors....
DUS (Distinctness, Uniformity and Stability) testing of new varieties is an important method for peanut germplasm evaluation identification varieties. In order to verify the feasibility variety based on image processing, 2000 pod images from 20 were obtained by a scanner. Initially, six traits quantified using mathematical processing technology, then, size, shape, color texture features (total 31) also extracted. Next, Fisher algorithm was used as feature selection select 'good' extracted...
Soil salinization poses a critical challenge to global food security, impacting plant growth, development, and crop yield. This study investigates the efficacy of deep learning techniques alongside chlorophyll fluorescence (ChlF) imaging technology for discerning varying levels salt stress in soybean seedlings. Traditional methods identification plants are often laborious time-intensive, prompting exploration more efficient approaches. A total six classic convolutional neural network (CNN)...
The accurate identification and classification of soybean mutant lines is essential for developing new plant varieties through mutation breeding. However, most existing studies have focused on the varieties. Distinguishing solely by their seeds can be challenging due to high genetic similarities. Therefore, in this paper, we designed a dual-branch convolutional neural network (CNN) composed two identical single CNNs fuse image features pods together solve line problem. Four (AlexNet,...