大型鱼类数据集

大型鱼类数据集

原文：

A Large Scale Fish Dataset

A Large-Scale Dataset for Fish Segmentation and Classification

This dataset contains 9 different seafood types collected from a supermarket in Izmir, Turkey for a university-industry collaboration project at Izmir University of Economics, and this work was published in ASYU 2020. Dataset includes, gilt head bream, red sea bream, sea bass, red mullet, horse mackerel, black sea sprat, striped red mullet, trout, shrimp image samples.

This dataset was collected in order to carry out segmentation, feature extraction and classification tasks and compare the common segmentation, feature extraction and classification algortihms (Semantic Segmentation, Convolutional Neural Networks, Bag of Features). All of the experiment results prove the usability of our dataset for purposes mentioned above.

Images were collected via 2 different cameras, Kodak Easyshare Z650 and Samsung ST60. Therefore, the resolution of the images are 2832 x 2128, 1024 x 768, respectively. Before the segmentation, feature extraction and classification process, the dataset was resized to 590 x 445 by preserving the aspect ratio. After resizing the images, all labels in the dataset were augmented (by flipping and rotating). At the end of the augmentation process, the number of total images for each class became 2000; 1000 for the RGB fish images and 1000 for their pair-wise ground truth labels.

The dataset contains 9 different seafood types. For each class, there are 1000 augmented images and their pair-waise augmented ground truths. Each class can be found in the "Fish_Dataset" file with their ground truth labels. All images for each class are ordered from "00000.png" to "01000.png". For example, if you want to access the ground truth images of the shrimp in the dataset, the order should be followed is "Fish->Shrimp->Shrimp GT".

译文：

大型鱼类数据集

用于鱼类分割和分类的大规模数据集

该数据集包含9种不同的海鲜类型收集从超市在土耳其伊兹密尔，为一个大学工业合作项目在伊兹密尔经济大学，这项工作发表在ASU 2020。数据集包括：金头鲷、红海鲷、鲈鱼、红鲻鱼、马鲭鱼、黑海鲱鱼、条纹红鲻鱼、鳟鱼、虾图像样本。

收集该数据集是为了执行分割、特征提取和分类任务，并比较常用的分割、特征提取和分类算法（语义分割、卷积神经网络、特征包）。所有的实验结果都证明了我们的数据集对于上述目的的可用性。

图像是通过柯达易共享Z650和三星ST60两种不同的相机采集的。因此，28321024个图像的分辨率分别为283276x。在分割、特征提取和分类过程之前，通过保留纵横比将数据集的大小调整为590 x 445。在调整图像大小后，数据集中的所有标签都被增加（通过翻转和旋转）。在增强过程结束时，每个类的总图像数为2000；1000个用于RGB鱼类图像，1000个用于它们的成对地面真相标签。

该数据集包含9种不同的海鲜类型。每门课都有1000张增强图像和一对增强的地面真相。每个类都可以在“Fish_数据集”文件中找到，其中包含它们的基本真相标签。每个类的所有图像都从“00000.png”到“01000.png”排序。例如，如果要访问数据集中虾的地面真实图像，应遵循的顺序是“Fish->Shrimp->Shrimp GT”。

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。