找出这两个图像之间的区别

Question

以编程方式，我的代码正在检测两类图像之间的差异，并且始终拒绝一类，而始终允许另一类。

我还没有发现产生错误的图像和不产生错误的图像之间有什么区别。但是必须有一些区别，因为产生错误的那些在 100% 的时间内都会这样做，而其他的则在 100% 的时间内按预期工作。

特别是，我检查了两组颜色格式：RGB；尺寸：无显着差异；数据类型：uint8 在两者中；像素值的大小：两者相似。

下面是两张永远无法使用的图片，然后是两张始终可以使用的图片：

• 此图片无法使用：https://www.colourbox.com/preview/11906131-maple-tree-and-grass-silhouette.jpg

• 此图片无法使用：http://feldmanphoto.com/wp-content/uploads/awe-inspiring-house-clipart-black-and-white-disney-coloring-pages-big-clipartxtras-illistration-background-housewives-bouncy.jpeg

• 此图像始终有效：http://www.spacedesign.us/wp-content/uploads/landscape-with-old-tree-and-grass-over-white-background-black-and-black-and-white-trees.jpg

• 此图像始终有效：http://www.modernhouse.co/wp-content/uploads/2017/07/1024px-RoseSeidlerHouseSulmanPrize.jpg

我怎样才能发现差异？

场景是我使用 Firebase 和 Swift iOS 前端将这些图像发送到 Google Cloud ML 引擎托管的 convnet。有些图像一直有效，而另一些图像则永远不会像上面那样工作。此外，当我使用 gcloud 版本 predict CLI 时，所有图像都有效。对我来说，问题必然是图像中的某些东西。因此，我在这里为成像组发帖。出于完整性的要求，代码已包含在内。

index.js 文件代码包含：

'use strict';

const functions = require('firebase-functions');
const gcs = require('@google-cloud/storage');
const admin = require('firebase-admin');
const exec = require('child_process').exec;
const path = require('path');
const fs = require('fs');
const google = require('googleapis');
const sizeOf = require('image-size');

admin.initializeApp(functions.config().firebase);
const db = admin.firestore();
const rtdb = admin.database();
const dbRef = rtdb.ref();

function cmlePredict(b64img) {
    return new Promise((resolve, reject) => {
        google.auth.getApplicationDefault(function (err, authClient) {
            if (err) {
                reject(err);
            }
            if (authClient.createScopedRequired && authClient.createScopedRequired()) {
                authClient = authClient.createScoped([
                    'https://www.googleapis.com/auth/cloud-platform'
                ]);
            }

        var ml = google.ml({
           version: 'v1'
        });

        const params = {
            auth: authClient,
            name: 'projects/myproject-18865/models/my_model',
            resource: {
                instances: [
                {
                    "image_bytes": {
                    "b64": b64img
                    }
                }
                ]
            }
        };

        ml.projects.predict(params, (err, result) => {
            if (err) {
                reject(err);
            } else {
                resolve(result);
            }
        });
    });
});
}

function resizeImg(filepath) {
    return new Promise((resolve, reject) => {
        exec(`convert ${filepath} -resize 224x ${filepath}`, (err) => {
          if (err) {
            console.error('Failed to resize image', err);
            reject(err);
          } else {
            console.log('resized image successfully');
            resolve(filepath);
          }
        });
      });
}

exports.runPrediction = functions.storage.object().onChange((event) => {

    fs.rmdir('./tmp/', (err) => {
        if (err) {
            console.log('error deleting tmp/ dir');
        }
    });

const object = event.data;
const fileBucket = object.bucket;
const filePath = object.name;
const bucket = gcs().bucket(fileBucket);
const fileName = path.basename(filePath);
const file = bucket.file(filePath);

if (filePath.startsWith('images/')) {  
    const destination = '/tmp/' + fileName;
    console.log('got a new image', filePath);
    return file.download({
        destination: destination
    }).then(() => {
        if(sizeOf(destination).width > 224) {
            console.log('scaling image down...');
            return resizeImg(destination);
        } else {
            return destination;
        }
    }).then(() => {
        console.log('base64 encoding image...');
        let bitmap = fs.readFileSync(destination);
        return new Buffer(bitmap).toString('base64');
    }).then((b64string) => {
        console.log('sending image to CMLE...');
        return cmlePredict(b64string);
    }).then((result) => {
        console.log(`results just returned and is: ${result}`);  



        let predict_proba = result.predictions[0]

        const res_pred_val = Object.keys(predict_proba).map(k => predict_proba[k])
        const res_val = Object.keys(result).map(k => result[k])

        const class_proba = [1-res_pred_val,res_pred_val]
        const opera_proba_init = 1-res_pred_val
        const capitol_proba_init = res_pred_val-0

        // convert fraction double to percentage int
        let opera_proba = (Math.floor((opera_proba_init.toFixed(2))*100))|0
        let capitol_proba = (Math.floor((capitol_proba_init.toFixed(2))*100))|0
        let feature_list = ["houses", "trees"]


        let outlinedImgPath = '';
        let imageRef = db.collection('predicted_images').doc(filePath.slice(7));
               outlinedImgPath = `outlined_img/${filePath.slice(7)}`;
               imageRef.set({
                image_path: outlinedImgPath,
                opera_proba: opera_proba,
                capitol_proba: capitol_proba
            });

        let predRef = dbRef.child("prediction_categories");
        let arrayRef = dbRef.child("prediction_array");

    predRef.set({
            opera_proba: opera_proba,
            capitol_proba: capitol_proba,
            });

       arrayRef.set({first: {
           array_proba: [opera_proba,capitol_proba],
           brief_description: ["a","b"],
           more_details: ["aaaa","bbbb"],
           feature_list: feature_list},
        zummy1: "",
        zummy2: ""});

        return bucket.upload(destination, {destination: outlinedImgPath});

    });
} else {
    return 'not a new image';
}
}); 

Answer 1

问题是坏图像是灰度的，而不是我的模型所期望的 RGB。我最初是通过查看形状来检查的。但是“坏”图像有 3 个颜色通道，这 3 个通道中的每一个都存储相同的数字——所以我的模型拒绝接受它们。此外，正如预期的那样，与我最初观察到的相反，gcloud ML-engine predict CLI 实际上对于这些图像也失败了。我花了 2 天时间才弄清楚这一点！