增加回归特征

src/main/java/org/wlld/imageRecognition/Convolution.java

@@ -7,6 +7,7 @@ import org.wlld.imageRecognition.border.Border;
 import org.wlld.imageRecognition.border.Frame;
 import org.wlld.imageRecognition.border.FrameBody;
 import org.wlld.imageRecognition.modelEntity.RegressionBody;
+import org.wlld.imageRecognition.segmentation.RgbRegression;
 import org.wlld.tools.ArithUtil;
 import org.wlld.tools.Frequency;
 
@@ -186,7 +187,9 @@ public class Convolution extends Frequency {
         Collections.sort(rgbNorms, rgbSort);
         List<Double> features = new ArrayList<>();
         for (int i = 0; i < sqNub; i++) {
-            double[] rgb = rgbNorms.get(i).getRgb();
+            //double[] rgb = rgbNorms.get(i).getRgb();
+            RgbRegression rgbRegression = rgbNorms.get(i).getRgbRegression();
+            double[] rgb = new double[]{rgbRegression.getWr(), rgbRegression.getWg(), rgbRegression.getB()};
             for (int j = 0; j < 3; j++) {
                 features.add(rgb[j]);
             }

src/main/java/org/wlld/imageRecognition/MeanClustering.java

@@ -1,5 +1,7 @@
 package org.wlld.imageRecognition;
 
+import org.wlld.imageRecognition.segmentation.RgbRegression;
+
 import java.util.*;
 
 //K均值聚类
@@ -8,6 +10,7 @@ public class MeanClustering {
     private int length;//向量长度(模型需要返回)
     private int speciesQuantity;//种类数量(模型需要返回)
     private List<RGBNorm> matrices = new ArrayList<>();//均值K模型(模型需要返回)
+    private int size = 10000;
 
     public List<RGBNorm> getMatrices() {
         return matrices;
@@ -69,6 +72,23 @@ public class MeanClustering {
         }
     }
 
+    private void startRegression() throws Exception {//开始聚类回归
+        Random random = new Random();
+        for (RGBNorm rgbNorm : matrices) {
+            RgbRegression rgbRegression = new RgbRegression(size);
+            List<double[]> list = rgbNorm.getRgbs();
+            for (int i = 0; i < size; i++) {
+                double[] rgb = list.get(random.nextInt(list.size()));
+                rgb[0] = rgb[0] / 255;
+                rgb[1] = rgb[1] / 255;
+                rgb[2] = rgb[2] / 255;
+                rgbRegression.insertRGB(rgb);
+            }
+            rgbRegression.regression();
+            rgbNorm.setRgbRegression(rgbRegression);
+        }
+    }
+
     public void start() throws Exception {//开始聚类
         if (matrixList.size() > 1) {
             Random random = new Random();
@@ -81,16 +101,16 @@ public class MeanClustering {
             }
             //进行两者的比较
             boolean isNext;
-            for (int i = 0; i < 50; i++) {
+            for (int i = 0; i < 30; i++) {
                 averageMatrix();
                 isNext = isNext();
-                if (isNext) {
+                if (isNext && i < 29) {
                     clear();
                 } else {
                     break;
                 }
             }
-
+            startRegression();//开始进行回归
         } else {
             throw new Exception("matrixList number less than 2");
         }

src/main/java/org/wlld/imageRecognition/Operation.java

@@ -73,12 +73,12 @@ public class Operation {//进行计算
         for (int i = 0; i < size; i++) {
             int xr = random.nextInt(x);
             int yr = random.nextInt(y);
-            double[] rgb = new double[]{matrixR.getNumber(xr, yr), matrixG.getNumber(xr, yr),
-                    matrixB.getNumber(xr, yr)};
+            double[] rgb = new double[]{matrixR.getNumber(xr, yr) / 255, matrixG.getNumber(xr, yr) / 255,
+                    matrixB.getNumber(xr, yr) / 255};
             rgbRegression.insertRGB(rgb);
         }
         rgbRegression.regression();
-//        double[] rgb = new double[]{164, 189, 193};
+//        double[] rgb = new double[]{164 / 255, 189 / 255, 193 / 255};
 //        double dis = rgbRegression.getDisError(rgb);
 //        System.out.println("dis==" + dis);
         templeConfig.getFood().getTrayBody().add(rgbRegression);

src/main/java/org/wlld/imageRecognition/RGBNorm.java

@@ -1,13 +1,27 @@
 package org.wlld.imageRecognition;
 
+import org.wlld.imageRecognition.segmentation.RgbRegression;
 import org.wlld.tools.ArithUtil;
 
+import java.util.ArrayList;
+import java.util.List;
+
 public class RGBNorm {
     private double[] rgbAll = new double[3];
     private double norm;
     private int nub;
     private double[] rgb = new double[3];
     private double[] rgbUp;
+    private List<double[]> rgbs = new ArrayList<>();
+    private RgbRegression rgbRegression;
+
+    public RgbRegression getRgbRegression() {
+        return rgbRegression;
+    }
+
+    public void setRgbRegression(RgbRegression rgbRegression) {
+        this.rgbRegression = rgbRegression;
+    }
 
     RGBNorm(double[] rgb) {
         this.rgbUp = rgb;
@@ -17,12 +31,17 @@ public class RGBNorm {
         rgbUp = rgb;
     }
 
+    public List<double[]> getRgbs() {
+        return rgbs;
+    }
+
     public void clear() {
         rgbAll = new double[3];
         nub = 0;
         for (int i = 0; i < rgb.length; i++) {
             rgbUp[i] = rgb[i];
         }
+        rgbs.clear();
         //System.out.println("clear==" + Arrays.toString(rgbUp));
     }
 
@@ -57,6 +76,7 @@ public class RGBNorm {
         for (int i = 0; i < rgb.length; i++) {
             rgbAll[i] = rgbAll[i] + rgb[i];
         }
+        rgbs.add(rgb);
         nub++;
     }
 

src/main/java/org/wlld/imageRecognition/segmentation/RgbRegression.java

@@ -54,7 +54,7 @@ public class RgbRegression {
             wg = ws.getNumber(1, 0);
             b = ws.getNumber(2, 0);
             isRegression = true;
-            System.out.println("wr==" + wr + ",wg==" + wg + ",b==" + b);
+            // System.out.println("wr==" + wr + ",wg==" + wg + ",b==" + b);
         } else {
             throw new Exception("regression matrix size is zero");
         }

src/main/java/org/wlld/imageRecognition/segmentation/Watershed.java

@@ -73,11 +73,11 @@ public class Watershed {
 
     private boolean isTray(int x, int y) throws Exception {
         boolean isTray = false;
-        double[] rgb = new double[]{matrixR.getNumber(x, y), matrixG.getNumber(x, y),
-                matrixB.getNumber(x, y)};
+        double[] rgb = new double[]{matrixR.getNumber(x, y) / 255, matrixG.getNumber(x, y) / 255,
+                matrixB.getNumber(x, y) / 255};
         for (RgbRegression rgbRegression : trayBody) {
             double dist = rgbRegression.getDisError(rgb);
-            if (dist < 10) {
+            if (dist < 0) {
                 isTray = true;
                 break;
             }

src/main/java/org/wlld/param/Food.java

@@ -17,7 +17,7 @@ public class Food {
     private double rowMark = 0.12;//行痕迹过滤
     private double columnMark = 0.25;//列痕迹过滤
     private List<RgbRegression> trayBody = new ArrayList<>();//托盘实体参数
-    private int regressionNub = 70;//回归数据量
+    private int regressionNub = 10000;//回归次数
 
     public int getRegressionNub() {
         return regressionNub;

src/test/java/coverTest/FoodTest.java

@@ -53,14 +53,14 @@ public class FoodTest {
         Picture picture = new Picture();
         List<Specifications> specificationsList = new ArrayList<>();
         Specifications specifications = new Specifications();
-        specifications.setMinWidth(400);
-        specifications.setMinHeight(400);
+        specifications.setMinWidth(300);
+        specifications.setMinHeight(300);
         specifications.setMaxWidth(950);
         specifications.setMaxHeight(950);
         specificationsList.add(specifications);
         Operation operation = new Operation(templeConfig);
-        for (int i = 1; i <= 1; i++) {
-            ThreeChannelMatrix threeChannelMatrix1 = picture.getThreeMatrix("/Users/lidapeng/Documents/paramterTest/c" + i + ".jpg");
+        for (int i = 1; i <= 28; i++) {
+            ThreeChannelMatrix threeChannelMatrix1 = picture.getThreeMatrix("/Users/lidapeng/Desktop/foodModel/test1/g" + i + ".jpg");
             List<RegionBody> regionBody = operation.colorLook(threeChannelMatrix1, specificationsList);
             for (int j = 0; j < regionBody.size(); j++) {
                 RegionBody regionBody1 = regionBody.get(j);
@@ -89,7 +89,7 @@ public class FoodTest {
         //聚类
         templeConfig.setFeatureNub(3);//聚类特征数量
         //菜品识别实体类
-        food.setShrink(5);//缩紧像素
+        food.setShrink(20);//缩紧像素
         food.setTimes(2);//聚类数据增强
         food.setRowMark(0.1);//0.12
         food.setColumnMark(0.1);//0.25
@@ -114,14 +114,24 @@ public class FoodTest {
         specificationsList.add(specifications);
         ThreeChannelMatrix threeChannelMatrix = picture.getThreeMatrix("/Users/lidapeng/Desktop/myDocument/d.jpg");
         operation.setTray(threeChannelMatrix);
-        for (int i = 1; i <= 1; i++) {
-            ThreeChannelMatrix threeChannelMatrix1 = picture.getThreeMatrix("/Users/lidapeng/Desktop/test/e1.jpg");
+        for (int i = 1; i <= 10; i++) {
+            ThreeChannelMatrix threeChannelMatrix1 = picture.getThreeMatrix("/Users/lidapeng/Desktop/foodModel/a/a" + i + ".jpg");
+            ThreeChannelMatrix threeChannelMatrix2 = picture.getThreeMatrix("/Users/lidapeng/Desktop/foodModel/b/b" + i + ".jpg");
+            ThreeChannelMatrix threeChannelMatrix3 = picture.getThreeMatrix("/Users/lidapeng/Desktop/foodModel/c/c" + i + ".jpg");
+            ThreeChannelMatrix threeChannelMatrix4 = picture.getThreeMatrix("/Users/lidapeng/Desktop/foodModel/d/d" + i + ".jpg");
+            ThreeChannelMatrix threeChannelMatrix5 = picture.getThreeMatrix("/Users/lidapeng/Desktop/foodModel/e/e" + i + ".jpg");
+            ThreeChannelMatrix threeChannelMatrix6 = picture.getThreeMatrix("/Users/lidapeng/Desktop/foodModel/f/f" + i + ".jpg");
             operation.colorStudy(threeChannelMatrix1, 1, specificationsList);
-            System.out.println("=======================================");
+            operation.colorStudy(threeChannelMatrix2, 2, specificationsList);
+            operation.colorStudy(threeChannelMatrix3, 3, specificationsList);
+            operation.colorStudy(threeChannelMatrix4, 4, specificationsList);
+            operation.colorStudy(threeChannelMatrix5, 5, specificationsList);
+            operation.colorStudy(threeChannelMatrix6, 6, specificationsList);
+            System.out.println("=======================================" + i);
         }
 //        minX==301,minY==430,maxX==854,maxY==920
 //        minX==497,minY==1090,maxX==994,maxY==1520
-        //test2(templeConfig);
+        test2(templeConfig);
     }
 
     public static void study() throws Exception {