Soft-shell Shrimp Recognition Based on an Improved AlexNet for Quality Evaluations

被引:49
作者
Liu, Zihao [1 ]
机构
[1] Jiaxing Univ, Coll Math Phys & Informat Engn, Jiaxing 314001, Zhejiang, Peoples R China
关键词
Soft-shell shrimp; Mean accuracy precision; Deep-ShrimpNet;
D O I
10.1016/j.jfoodeng.2019.109698
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Shrimp quality evaluations fulfill an essential role in producing high-value shrimp products. The presence of soft-shell shrimp deteriorates the quality of shrimp products. The biggest challenge in preventing this is the similarity in appearance of soft-shell (s-shrimp) and sound (o-shrimp) shrimp from an imaging perspective. This similarity imposes significant limitations on distinguishing them with traditional machine vision methods. To circumvent this problem, a novel method based on deep convolutional neural networks (Deep-ShrimpNet) is proposed. Initially, several image processing steps were performed to normalize the shrimp image. Furthermore, four critical hyper-parameters (Le., batch-size, dropout ratio, learning rate and number (size) of local receptive fields) were optimized by a comparative analysis. Additionally, the self-learned combined features in each convolutional layer were visualized to explore the internal mechanism of Deep-ShrimpNet. To obtain the efficient strategy, an ablation study was also performed by removing layers of the CNNs. Finally, the superiority of the proposed algorithm was verified through a comparison with other sophisticated CNNs. In a test dataset, Deep-ShrimpNet achieved a mean accuracy precision (mAP) of 0.972 and modeling time of 0.54 h. The robust performance of the proposed method across the shrimp dataset indicates that Deep-ShrimpNet is promising for online shrimp classification and quality measurement.
引用
收藏
页数:10
相关论文
共 36 条
  • [1] Effect of the Temporal Gradient of Vegetation Indices on Early-Season Wheat Classification Using the Random Forest Classifier
    Abad, Mousa Saei Jamal
    Abkar, Ali A.
    Mojaradi, Barat
    [J]. APPLIED SCIENCES-BASEL, 2018, 8 (08):
  • [2] Symptom based automated detection of citrus diseases using color histogram and textural descriptors
    Ali, H.
    Lali, M. I.
    Nawaz, M. Z.
    Sharif, M.
    Saleem, B. A.
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2017, 138 : 92 - 104
  • [3] [Anonymous], 2016 ASABE ANN INT M
  • [4] [Anonymous], P C NAM C LOC
  • [5] [Anonymous], 5 INT S ADV OPT MAN
  • [6] [Anonymous], FOOD ANAL METHODS
  • [7] [Anonymous], INT AGR ENG J
  • [8] [Anonymous], STUDY ON LINE VERIFI
  • [9] An ANN algorithm for automatic, real-time tsunami detection in deep-sea level measurements
    Beltrami, Gian Mario
    [J]. OCEAN ENGINEERING, 2008, 35 (5-6) : 572 - 587
  • [10] Automatic, real-time detection and characterization of tsunamis in deep-sea level measurements
    Beltrami, Gian Mario
    [J]. OCEAN ENGINEERING, 2011, 38 (14-15) : 1677 - 1685