IMASHRIMP: Automatic White Shrimp (Penaeus vannamei) Biometrical Analysis from Laboratory Images Using Computer Vision and Deep Learning

• URL: http://arxiv.org/abs/2507.02519v1
• Date: Thu, 03 Jul 2025 10:32:49 GMT
• Title: IMASHRIMP: Automatic White Shrimp (Penaeus vannamei) Biometrical Analysis from Laboratory Images Using Computer Vision and Deep Learning
• Authors: Abiam Remache González, Meriem Chagour, Timon Bijan Rüth, Raúl Trapiella Cañedo, Marina Martínez Soler, Álvaro Lorenzo Felipe, Hyun-Suk Shin, María-Jesús Zamorano Serrano, Ricardo Torres, Juan-Antonio Castillo Parra, Eduardo Reyes Abad, Miguel-Ángel Ferrer Ballester, Juan-Manuel Afonso López, Francisco-Mario Hernández Tejera, Adrian Penate-Sanchez,
• Abstract summary: IMASHRIMP is an adapted system for the automated morphological analysis of white shrimp (Penaeus vannamei)<n>Existing deep learning and computer vision techniques were modified to address the specific challenges of shrimp morphology analysis from RGBD images.<n>IMASHRIMP incorporates two discrimination modules, based on a modified ResNet-50 architecture, to classify images by the point of view and determine rostrum integrity.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces IMASHRIMP, an adapted system for the automated morphological analysis of white shrimp (Penaeus vannamei}, aimed at optimizing genetic selection tasks in aquaculture. Existing deep learning and computer vision techniques were modified to address the specific challenges of shrimp morphology analysis from RGBD images. IMASHRIMP incorporates two discrimination modules, based on a modified ResNet-50 architecture, to classify images by the point of view and determine rostrum integrity. It is proposed a "two-factor authentication (human and IA)" system, it reduces human error in view classification from 0.97% to 0% and in rostrum detection from 12.46% to 3.64%. Additionally, a pose estimation module was adapted from VitPose to predict 23 key points on the shrimp's skeleton, with separate networks for lateral and dorsal views. A morphological regression module, using a Support Vector Machine (SVM) model, was integrated to convert pixel measurements to centimeter units. Experimental results show that the system effectively reduces human error, achieving a mean average precision (mAP) of 97.94% for pose estimation and a pixel-to-centimeter conversion error of 0.07 (+/- 0.1) cm. IMASHRIMP demonstrates the potential to automate and accelerate shrimp morphological analysis, enhancing the efficiency of genetic selection and contributing to more sustainable aquaculture practices.The code are available at https://github.com/AbiamRemacheGonzalez/ImaShrimp-public

Related papers

• A Dual-Feature Extractor Framework for Accurate Back Depth and Spine Morphology Estimation from Monocular RGB Images [15.19284295210246]
  We propose a novel pipeline to accurately estimate the depth information of the unclothed back.<n>We then estimate spine morphology by integrating both depth and surface information.<n>This integrated approach enhances the accuracy of spine curve generation, achieving an impressive performance of up to 97%.
  arXiv  Detail & Related papers  (2025-07-30T13:55:37Z)
• FishDet-M: A Unified Large-Scale Benchmark for Robust Fish Detection and CLIP-Guided Model Selection in Diverse Aquatic Visual Domains [1.3791394805787949]
  FishDet-M is the largest unified benchmark for fish detection, comprising 13 publicly available datasets spanning diverse aquatic environments.<n>All data are harmonized using COCO-style annotations with both bounding boxes and segmentation masks.<n>FishDet-M establishes a standardized and reproducible platform for evaluating object detection in complex aquatic scenes.
  arXiv  Detail & Related papers  (2025-07-23T18:32:01Z)
• The Phantom of the Elytra -- Phylogenetic Trait Extraction from Images of Rove Beetles Using Deep Learning -- Is the Mask Enough? [1.0742675209112622]
  Phylogenetic analysis traditionally relies on labor-intensive manual extraction of morphological traits.<n>Recent advances in deep learning offer the potential to automate this process.<n>We compare the performance of deep learning models using three distinct morphological representations.
  arXiv  Detail & Related papers  (2025-02-06T22:41:50Z)
• PIGUIQA: A Physical Imaging Guided Perceptual Framework for Underwater Image Quality Assessment [59.9103803198087]
  We propose a Physical Imaging Guided perceptual framework for Underwater Image Quality Assessment (UIQA)<n>By leveraging underwater radiative transfer theory, we integrate physics-based imaging estimations to establish quantitative metrics for these distortions.<n>The proposed model accurately predicts image quality scores and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-20T03:31:45Z)
• LVS-Net: A Lightweight Vessels Segmentation Network for Retinal Image Analysis [1.347667211255822]
  This paper presents a novel lightweight encoder-decoder model that segments retinal vessels to improve the efficiency of disease detection.<n>It incorporates multi-scale convolutional blocks in the encoder to accurately identify vessels of various sizes and thicknesses.<n>It outperforms existing models with dice scores of 86.44%, 84.22%, and 87.88%, respectively.
  arXiv  Detail & Related papers  (2024-12-08T15:21:37Z)
• Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding [6.332060647845203]
  We introduce FishPhenoKey, a comprehensive dataset comprising 23,331 high-resolution images spanning six fish species. FishPhenoKey includes 22 phenotype-oriented annotations, enabling the capture of intricate morphological phenotypes. We also propose a new evaluation metric, Percentage of Measured Phenotype.
  arXiv  Detail & Related papers  (2024-05-21T03:36:13Z)
• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
  This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection. Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels. Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-03-19T09:28:19Z)
• Prawn Morphometrics and Weight Estimation from Images using Deep Learning for Landmark Localization [2.778518997767646]
  We developed a novel approach to automate weight estimation and morphometric analysis using the black tiger prawn (Penaeus monodon) as a model crustacean. For morphometric analyses, we utilized the detected landmarks to derive five important prawn traits. Our experimental results demonstrate that the novel DL approach outperforms existing DL methods in terms of accuracy, robustness, and efficiency.
  arXiv  Detail & Related papers  (2023-07-15T07:05:06Z)
• Optimizations of Autoencoders for Analysis and Classification of Microscopic In Situ Hybridization Images [68.8204255655161]
  We propose a deep-learning framework to detect and classify areas of microscopic images with similar levels of gene expression. The data we analyze requires an unsupervised learning model for which we employ a type of Artificial Neural Network - Deep Learning Autoencoders.
  arXiv  Detail & Related papers  (2023-04-19T13:45:28Z)
• A kinetic approach to consensus-based segmentation of biomedical images [39.58317527488534]
  We apply a kinetic version of a bounded confidence consensus model to biomedical segmentation problems. The large time behavior of the system is then computed with the aid of a surrogate Fokker-Planck approach. We minimize the introduced segmentation metric for a relevant set of 2D gray-scale images.
  arXiv  Detail & Related papers  (2022-11-08T09:54:34Z)
• Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation [51.916106055115755]
  We propose a new CNN architecture that is pose and scale invariant thanks to the use of Spatial Transformer Network (STN) Our architecture is composed of three sequential modules that are estimated together during training. We test the proposed method in kidney and renal tumor segmentation on abdominal pediatric CT scanners.
  arXiv  Detail & Related papers  (2021-07-06T14:50:03Z)
• Appearance Learning for Image-based Motion Estimation in Tomography [60.980769164955454]
  In tomographic imaging, anatomical structures are reconstructed by applying a pseudo-inverse forward model to acquired signals. Patient motion corrupts the geometry alignment in the reconstruction process resulting in motion artifacts. We propose an appearance learning approach recognizing the structures of rigid motion independently from the scanned object.
  arXiv  Detail & Related papers  (2020-06-18T09:49:11Z)
• Automatic image-based identification and biomass estimation of invertebrates [70.08255822611812]
  Time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. We propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We use state-of-the-art Resnet-50 and InceptionV3 CNNs for the classification task.
  arXiv  Detail & Related papers  (2020-02-05T21:38:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.