我应该对图像进行灰度处理吗? [英] Should I gray scale the image?

问题描述

我正在使用来自tensorflow的R-CNN对象检测库对图像中的30种衣服进行分类: https://github.com/tensorflow/models/tree/master/research/object_detection

I'm categorizing 30 types of clothes from the image using R-CNN Object Detection Library from tensorflow : https://github.com/tensorflow/models/tree/master/research/object_detection

当我们收集图像进行训练和测试时，颜色重要吗?

Does color matter when we collect images for training and testing?

如果我只穿紫色和蓝色衬衫，我猜它不会认出红色衬衫吗?

If I put only purple and blue shirts, I guess it won't recognize red shirts?

我应该对所有图像进行灰度处理以检测衣服的类型吗? :)

Should I gray scale all images to detect the types of clothes? :)

推荐答案

是的，颜色很重要.潜在的视觉特征提取基于卷积神经网络，该神经网络经过预先训练，可以对ImageNet数据集中的彩色图像执行图像识别.

Yes, colour does matter. The underlying visual feature extraction is based on a convolutional neural network, pre-trained to perform image recognition on colour images in the ImageNet dataset.

引入R-CNN存储库说明您自己的数据集要求提供RGB图像.

The R-CNN repository instructions on bringing in your own dataset asks for RGB images.

数据集要求

Dataset Requirements

对于数据集中的每个示例，您应该具有以下信息:

For every example in your dataset, you should have the following information:

1. 编码为jpeg或png的数据集的RGB图像.
2. 图像边框的列表.每个边界框应包含:
   • 由4个浮点数[ymin，xmin，ymax，xmax]定义的边界框坐标(原点位于左上角).请注意，我们将归一化的坐标(x/宽度，y/高度)存储在TFRecord数据集中.
   • 边界框中对象的类.

1. An RGB image for the dataset encoded as jpeg or png.
2. A list of bounding boxes for the image. Each bounding box should contain:
   • A bounding box coordinates (with origin in top left corner) defined by 4 floating point numbers [ymin, xmin, ymax, xmax]. Note that we store the normalized coordinates (x / width, y / height) in the TFRecord dataset.
   • The class of the object in the bounding box.

这篇关于我应该对图像进行灰度处理吗?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！