简介：测试了七段数字图片段角度对于识别的影响。可以看到对于6,9两个数字，在旋转过程中他们之间会相互转换。2,5在旋转180°之后，它们与自己相同，会出现两个识别相同。0,8与其他数字自检有着比较多的差异。 1,7两个数字有着较强的交叉。

关键词： 七段数字，LCD

#mermaid-svg-V1oEDEal6v6oziCP .label{font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family);fill:#333;color:#333}#mermaid-svg-V1oEDEal6v6oziCP .label text{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .node rect,#mermaid-svg-V1oEDEal6v6oziCP .node circle,#mermaid-svg-V1oEDEal6v6oziCP .node ellipse,#mermaid-svg-V1oEDEal6v6oziCP .node polygon,#mermaid-svg-V1oEDEal6v6oziCP .node path{fill:#ECECFF;stroke:#9370db;stroke-width:1px}#mermaid-svg-V1oEDEal6v6oziCP .node .label{text-align:center;fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .node.clickable{cursor:pointer}#mermaid-svg-V1oEDEal6v6oziCP .arrowheadPath{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .edgePath .path{stroke:#333;stroke-width:1.5px}#mermaid-svg-V1oEDEal6v6oziCP .flowchart-link{stroke:#333;fill:none}#mermaid-svg-V1oEDEal6v6oziCP .edgeLabel{background-color:#e8e8e8;text-align:center}#mermaid-svg-V1oEDEal6v6oziCP .edgeLabel rect{opacity:0.9}#mermaid-svg-V1oEDEal6v6oziCP .edgeLabel span{color:#333}#mermaid-svg-V1oEDEal6v6oziCP .cluster rect{fill:#ffffde;stroke:#aa3;stroke-width:1px}#mermaid-svg-V1oEDEal6v6oziCP .cluster text{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family);font-size:12px;background:#ffffde;border:1px solid #aa3;border-radius:2px;pointer-events:none;z-index:100}#mermaid-svg-V1oEDEal6v6oziCP .actor{stroke:#ccf;fill:#ECECFF}#mermaid-svg-V1oEDEal6v6oziCP text.actor>tspan{fill:#000;stroke:none}#mermaid-svg-V1oEDEal6v6oziCP .actor-line{stroke:grey}#mermaid-svg-V1oEDEal6v6oziCP .messageLine0{stroke-width:1.5;stroke-dasharray:none;stroke:#333}#mermaid-svg-V1oEDEal6v6oziCP .messageLine1{stroke-width:1.5;stroke-dasharray:2, 2;stroke:#333}#mermaid-svg-V1oEDEal6v6oziCP #arrowhead path{fill:#333;stroke:#333}#mermaid-svg-V1oEDEal6v6oziCP .sequenceNumber{fill:#fff}#mermaid-svg-V1oEDEal6v6oziCP #sequencenumber{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP #crosshead path{fill:#333;stroke:#333}#mermaid-svg-V1oEDEal6v6oziCP .messageText{fill:#333;stroke:#333}#mermaid-svg-V1oEDEal6v6oziCP .labelBox{stroke:#ccf;fill:#ECECFF}#mermaid-svg-V1oEDEal6v6oziCP .labelText,#mermaid-svg-V1oEDEal6v6oziCP .labelText>tspan{fill:#000;stroke:none}#mermaid-svg-V1oEDEal6v6oziCP .loopText,#mermaid-svg-V1oEDEal6v6oziCP .loopText>tspan{fill:#000;stroke:none}#mermaid-svg-V1oEDEal6v6oziCP .loopLine{stroke-width:2px;stroke-dasharray:2, 2;stroke:#ccf;fill:#ccf}#mermaid-svg-V1oEDEal6v6oziCP .note{stroke:#aa3;fill:#fff5ad}#mermaid-svg-V1oEDEal6v6oziCP .noteText,#mermaid-svg-V1oEDEal6v6oziCP .noteText>tspan{fill:#000;stroke:none}#mermaid-svg-V1oEDEal6v6oziCP .activation0{fill:#f4f4f4;stroke:#666}#mermaid-svg-V1oEDEal6v6oziCP .activation1{fill:#f4f4f4;stroke:#666}#mermaid-svg-V1oEDEal6v6oziCP .activation2{fill:#f4f4f4;stroke:#666}#mermaid-svg-V1oEDEal6v6oziCP .mermaid-main-font{font-family:"trebuchet ms", verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .section{stroke:none;opacity:0.2}#mermaid-svg-V1oEDEal6v6oziCP .section0{fill:rgba(102,102,255,0.49)}#mermaid-svg-V1oEDEal6v6oziCP .section2{fill:#fff400}#mermaid-svg-V1oEDEal6v6oziCP .section1,#mermaid-svg-V1oEDEal6v6oziCP .section3{fill:#fff;opacity:0.2}#mermaid-svg-V1oEDEal6v6oziCP .sectionTitle0{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .sectionTitle1{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .sectionTitle2{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .sectionTitle3{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .sectionTitle{text-anchor:start;font-size:11px;text-height:14px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .grid .tick{stroke:#d3d3d3;opacity:0.8;shape-rendering:crispEdges}#mermaid-svg-V1oEDEal6v6oziCP .grid .tick text{font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .grid path{stroke-width:0}#mermaid-svg-V1oEDEal6v6oziCP .today{fill:none;stroke:red;stroke-width:2px}#mermaid-svg-V1oEDEal6v6oziCP .task{stroke-width:2}#mermaid-svg-V1oEDEal6v6oziCP .taskText{text-anchor:middle;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .taskText:not([font-size]){font-size:11px}#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutsideRight{fill:#000;text-anchor:start;font-size:11px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutsideLeft{fill:#000;text-anchor:end;font-size:11px}#mermaid-svg-V1oEDEal6v6oziCP .task.clickable{cursor:pointer}#mermaid-svg-V1oEDEal6v6oziCP .taskText.clickable{cursor:pointer;fill:#003163 !important;font-weight:bold}#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutsideLeft.clickable{cursor:pointer;fill:#003163 !important;font-weight:bold}#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutsideRight.clickable{cursor:pointer;fill:#003163 !important;font-weight:bold}#mermaid-svg-V1oEDEal6v6oziCP .taskText0,#mermaid-svg-V1oEDEal6v6oziCP .taskText1,#mermaid-svg-V1oEDEal6v6oziCP .taskText2,#mermaid-svg-V1oEDEal6v6oziCP .taskText3{fill:#fff}#mermaid-svg-V1oEDEal6v6oziCP .task0,#mermaid-svg-V1oEDEal6v6oziCP .task1,#mermaid-svg-V1oEDEal6v6oziCP .task2,#mermaid-svg-V1oEDEal6v6oziCP .task3{fill:#8a90dd;stroke:#534fbc}#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutside0,#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutside2{fill:#000}#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutside1,#mermaid-svg-V1oEDEal6v6oziCP .taskTextOutside3{fill:#000}#mermaid-svg-V1oEDEal6v6oziCP .active0,#mermaid-svg-V1oEDEal6v6oziCP .active1,#mermaid-svg-V1oEDEal6v6oziCP .active2,#mermaid-svg-V1oEDEal6v6oziCP .active3{fill:#bfc7ff;stroke:#534fbc}#mermaid-svg-V1oEDEal6v6oziCP .activeText0,#mermaid-svg-V1oEDEal6v6oziCP .activeText1,#mermaid-svg-V1oEDEal6v6oziCP .activeText2,#mermaid-svg-V1oEDEal6v6oziCP .activeText3{fill:#000 !important}#mermaid-svg-V1oEDEal6v6oziCP .done0,#mermaid-svg-V1oEDEal6v6oziCP .done1,#mermaid-svg-V1oEDEal6v6oziCP .done2,#mermaid-svg-V1oEDEal6v6oziCP .done3{stroke:grey;fill:#d3d3d3;stroke-width:2}#mermaid-svg-V1oEDEal6v6oziCP .doneText0,#mermaid-svg-V1oEDEal6v6oziCP .doneText1,#mermaid-svg-V1oEDEal6v6oziCP .doneText2,#mermaid-svg-V1oEDEal6v6oziCP .doneText3{fill:#000 !important}#mermaid-svg-V1oEDEal6v6oziCP .crit0,#mermaid-svg-V1oEDEal6v6oziCP .crit1,#mermaid-svg-V1oEDEal6v6oziCP .crit2,#mermaid-svg-V1oEDEal6v6oziCP .crit3{stroke:#f88;fill:red;stroke-width:2}#mermaid-svg-V1oEDEal6v6oziCP .activeCrit0,#mermaid-svg-V1oEDEal6v6oziCP .activeCrit1,#mermaid-svg-V1oEDEal6v6oziCP .activeCrit2,#mermaid-svg-V1oEDEal6v6oziCP .activeCrit3{stroke:#f88;fill:#bfc7ff;stroke-width:2}#mermaid-svg-V1oEDEal6v6oziCP .doneCrit0,#mermaid-svg-V1oEDEal6v6oziCP .doneCrit1,#mermaid-svg-V1oEDEal6v6oziCP .doneCrit2,#mermaid-svg-V1oEDEal6v6oziCP .doneCrit3{stroke:#f88;fill:#d3d3d3;stroke-width:2;cursor:pointer;shape-rendering:crispEdges}#mermaid-svg-V1oEDEal6v6oziCP .milestone{transform:rotate(45deg) scale(0.8, 0.8)}#mermaid-svg-V1oEDEal6v6oziCP .milestoneText{font-style:italic}#mermaid-svg-V1oEDEal6v6oziCP .doneCritText0,#mermaid-svg-V1oEDEal6v6oziCP .doneCritText1,#mermaid-svg-V1oEDEal6v6oziCP .doneCritText2,#mermaid-svg-V1oEDEal6v6oziCP .doneCritText3{fill:#000 !important}#mermaid-svg-V1oEDEal6v6oziCP .activeCritText0,#mermaid-svg-V1oEDEal6v6oziCP .activeCritText1,#mermaid-svg-V1oEDEal6v6oziCP .activeCritText2,#mermaid-svg-V1oEDEal6v6oziCP .activeCritText3{fill:#000 !important}#mermaid-svg-V1oEDEal6v6oziCP .titleText{text-anchor:middle;font-size:18px;fill:#000;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP g.classGroup text{fill:#9370db;stroke:none;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family);font-size:10px}#mermaid-svg-V1oEDEal6v6oziCP g.classGroup text .title{font-weight:bolder}#mermaid-svg-V1oEDEal6v6oziCP g.clickable{cursor:pointer}#mermaid-svg-V1oEDEal6v6oziCP g.classGroup rect{fill:#ECECFF;stroke:#9370db}#mermaid-svg-V1oEDEal6v6oziCP g.classGroup line{stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP .classLabel .box{stroke:none;stroke-width:0;fill:#ECECFF;opacity:0.5}#mermaid-svg-V1oEDEal6v6oziCP .classLabel .label{fill:#9370db;font-size:10px}#mermaid-svg-V1oEDEal6v6oziCP .relation{stroke:#9370db;stroke-width:1;fill:none}#mermaid-svg-V1oEDEal6v6oziCP .dashed-line{stroke-dasharray:3}#mermaid-svg-V1oEDEal6v6oziCP #compositionStart{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP #compositionEnd{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP #aggregationStart{fill:#ECECFF;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP #aggregationEnd{fill:#ECECFF;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP #dependencyStart{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP #dependencyEnd{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP #extensionStart{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP #extensionEnd{fill:#9370db;stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP .commit-id,#mermaid-svg-V1oEDEal6v6oziCP .commit-msg,#mermaid-svg-V1oEDEal6v6oziCP .branch-label{fill:lightgrey;color:lightgrey;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .pieTitleText{text-anchor:middle;font-size:25px;fill:#000;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .slice{font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP g.stateGroup text{fill:#9370db;stroke:none;font-size:10px;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP g.stateGroup text{fill:#9370db;fill:#333;stroke:none;font-size:10px}#mermaid-svg-V1oEDEal6v6oziCP g.statediagram-cluster .cluster-label text{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP g.stateGroup .state-title{font-weight:bolder;fill:#000}#mermaid-svg-V1oEDEal6v6oziCP g.stateGroup rect{fill:#ECECFF;stroke:#9370db}#mermaid-svg-V1oEDEal6v6oziCP g.stateGroup line{stroke:#9370db;stroke-width:1}#mermaid-svg-V1oEDEal6v6oziCP .transition{stroke:#9370db;stroke-width:1;fill:none}#mermaid-svg-V1oEDEal6v6oziCP .stateGroup .composit{fill:white;border-bottom:1px}#mermaid-svg-V1oEDEal6v6oziCP .stateGroup .alt-composit{fill:#e0e0e0;border-bottom:1px}#mermaid-svg-V1oEDEal6v6oziCP .state-note{stroke:#aa3;fill:#fff5ad}#mermaid-svg-V1oEDEal6v6oziCP .state-note text{fill:black;stroke:none;font-size:10px}#mermaid-svg-V1oEDEal6v6oziCP .stateLabel .box{stroke:none;stroke-width:0;fill:#ECECFF;opacity:0.7}#mermaid-svg-V1oEDEal6v6oziCP .edgeLabel text{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .stateLabel text{fill:#000;font-size:10px;font-weight:bold;font-family:'trebuchet ms', verdana, arial;font-family:var(--mermaid-font-family)}#mermaid-svg-V1oEDEal6v6oziCP .node circle.state-start{fill:black;stroke:black}#mermaid-svg-V1oEDEal6v6oziCP .node circle.state-end{fill:black;stroke:white;stroke-width:1.5}#mermaid-svg-V1oEDEal6v6oziCP #statediagram-barbEnd{fill:#9370db}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-cluster rect{fill:#ECECFF;stroke:#9370db;stroke-width:1px}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-cluster rect.outer{rx:5px;ry:5px}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-state .divider{stroke:#9370db}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-state .title-state{rx:5px;ry:5px}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-cluster.statediagram-cluster .inner{fill:white}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-cluster.statediagram-cluster-alt .inner{fill:#e0e0e0}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-cluster .inner{rx:0;ry:0}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-state rect.basic{rx:5px;ry:5px}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-state rect.divider{stroke-dasharray:10,10;fill:#efefef}#mermaid-svg-V1oEDEal6v6oziCP .note-edge{stroke-dasharray:5}#mermaid-svg-V1oEDEal6v6oziCP .statediagram-note rect{fill:#fff5ad;stroke:#aa3;stroke-width:1px;rx:0;ry:0}:root{--mermaid-font-family: '"trebuchet ms", verdana, arial';--mermaid-font-family: "Comic Sans MS", "Comic Sans", cursive}#mermaid-svg-V1oEDEal6v6oziCP .error-icon{fill:#522}#mermaid-svg-V1oEDEal6v6oziCP .error-text{fill:#522;stroke:#522}#mermaid-svg-V1oEDEal6v6oziCP .edge-thickness-normal{stroke-width:2px}#mermaid-svg-V1oEDEal6v6oziCP .edge-thickness-thick{stroke-width:3.5px}#mermaid-svg-V1oEDEal6v6oziCP .edge-pattern-solid{stroke-dasharray:0}#mermaid-svg-V1oEDEal6v6oziCP .edge-pattern-dashed{stroke-dasharray:3}#mermaid-svg-V1oEDEal6v6oziCP .edge-pattern-dotted{stroke-dasharray:2}#mermaid-svg-V1oEDEal6v6oziCP .marker{fill:#333}#mermaid-svg-V1oEDEal6v6oziCP .marker.cross{stroke:#333}:root { --mermaid-font-family: "trebuchet ms", verdana, arial;}#mermaid-svg-V1oEDEal6v6oziCP {color: rgba(0, 0, 0, 0.75);font: ;}

旋转图片

目录
Contents

旋转图片

分割形成旋转图片

模型识别结果

网络识别代码

绘制结果

旋转总结

模型识别数字

▲ 图1 旋转的模式

§01 旋转图片

在博文 模型扫描识别图片 对于 七段数码数字模型 进行扫描测试，也就是利用对七段数码图片进行扫描识别，给出了波动的结果。

下面测试一下数字旋转对应的输出结果。

1.1 旋转图片

选择下面LED图片中的数码图像作为旋转测试。

▲ 图1.1.1 用于旋转测试的图片

1.1.1 分割形成旋转图片

（1）分割代码

from headm import *                 # =
import cv2
from paddle.vision.transforms import rotatebackgroundfile = '/home/aistudio/work/7seg/rotate/220112235650.BMP'
img = cv2.imread(backgroundfile)
printt(img.shape)backcolor = mean(mean(mean(img, axis=0), axis=0))
printt(backcolor)imgfile1 = '/home/aistudio/work/7seg/rotate/052-01234.JPG'
imgfile2 = '/home/aistudio/work/7seg/rotate/053-56789.JPG'cutdir = '/home/aistudio/work/7seg/rotate/cutdir'outsize = 48
rotateangle = range(0, 360, 10)def cutimg(imgfile):img = cv2.imread(imgfile)gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)imgwidth = gray.shape[1]imgheight = gray.shape[0]for i in range(5):left = int(imgwidth * i // 5)right = int(imgwidth * (i + 1) // 5)data = gray[:, left:right]data = cv2.resize(data, (outsize,outsize))for r in rotateangle:bgdim = ones((512,512)) * backcolorn1 = 256-24n2 = 256+24bgdim[n1:n2, n1:n2] = datarotdata = rotate(bgdim, r)data1 = rotdata[n1:n2,n1:n2]fn = os.path.join(cutdir, '%d_%03d.BMP'%(i+5, r))cv2.imwrite(fn, data1)cutimg(imgfile2)

（2）分割旋转结果

▲ 图1.1.2 旋转后的结果

from headm import *                 # =
import cv2cutdir = '/home/aistudio/work/7seg/rotate/cutdir'
filedim = os.listdir(cutdir)rotateangle = range(0, 360, 10)gifpath = '/home/aistudio/GIF'
if not os.path.isdir(gifpath):os.makedirs(gifpath)
gifdim = os.listdir(gifpath)
for f in gifdim:fn = os.path.join(gifpath, f)if os.path.isfile(fn):os.remove(fn)count = 0
for r in rotateangle:plt.clf()plt.figure(figsize=(10, 4))for i in range(2):for j in range(5):n = i*5+jfn = os.path.join(cutdir, '%d_%03d.BMP'%(n, r))img = cv2.imread(fn)plt.subplot(2,5,i*5+j+1)plt.imshow(img)savefile = os.path.join(gifpath, '%03d.jpg'%count)count += 1plt.savefig(savefile)

▲ 图数字旋转

1.2 模型识别结果

1.2.1 网络识别代码

import sys,os,math,time
sys.path.append("/home/aistudio/external-libraries")
import matplotlib.pyplot as plt
from numpy import *import paddle
import paddle.fluid as fluid
import cv2
import cv2imgwidth = 48
imgheight = 48
inputchannel = 1
kernelsize   = 5
targetsize = 10
ftwidth = ((imgwidth-kernelsize+1)//2-kernelsize+1)//2
ftheight = ((imgheight-kernelsize+1)//2-kernelsize+1)//2class lenet(paddle.nn.Layer):def __init__(self, ):super(lenet, self).__init__()self.conv1 = paddle.nn.Conv2D(in_channels=inputchannel, out_channels=6, kernel_size=kernelsize, stride=1, padding=0)self.conv2 = paddle.nn.Conv2D(in_channels=6, out_channels=16, kernel_size=kernelsize, stride=1, padding=0)self.mp1    = paddle.nn.MaxPool2D(kernel_size=2, stride=2)self.mp2    = paddle.nn.MaxPool2D(kernel_size=2, stride=2)self.L1     = paddle.nn.Linear(in_features=ftwidth*ftheight*16, out_features=120)self.L2     = paddle.nn.Linear(in_features=120, out_features=86)self.L3     = paddle.nn.Linear(in_features=86, out_features=targetsize)def forward(self, x):x = self.conv1(x)x = paddle.nn.functional.relu(x)x = self.mp1(x)x = self.conv2(x)x = paddle.nn.functional.relu(x)x = self.mp2(x)x = paddle.flatten(x, start_axis=1, stop_axis=-1)x = self.L1(x)x = paddle.nn.functional.relu(x)x = self.L2(x)x = paddle.nn.functional.relu(x)x = self.L3(x)return xmodel = lenet()
model.set_state_dict(paddle.load('/home/aistudio/work/seg7model4_1_all.pdparams'))

cutdir = '/home/aistudio/work/7seg/rotate/cutdir'
rotateangle = range(0, 360, 10)def modelpre(n, degree):fn = os.path.join(cutdir, '%d_%03d.BMP'%(n, degree))img = cv2.imread(fn)data = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)data = data - mean(data)stdd = std(data)data = data/stddinputs = data[newaxis, :, :]preid = model(paddle.to_tensor([inputs], dtype='float32'))return preid.numpy()outdim = []for r in rotateangle:out = modelpre(0, r)outdim.append(out[0])print(outdim)

1.2.2 绘制结果

plt.clf()
plt.figure(figsize=(10,6))
for i in range(10):plt.plot([a[i] for a in outdim], label='Out=%d'%i)plt.xlabel("Angle")
plt.ylabel("Value")
plt.grid(True)
plt.tight_layout()
plt.legend(loc='upper right')
plt.savefig('/home/aistudio/stdout.jpg')
plt.show()

▲ 图数字0旋转

▲ 图1.2.1 数字0旋转输出结果

▲ 图数字1旋转

▲ 图1.2.2 数字1旋转识别结果

▲ 图数字2旋转

▲ 图1.2.3 数字2旋转识别结果

▲ 图数字3旋转

▲ 图1.2.4 数字3旋转识别结果

▲ 图数字4旋转

▲ 图1.2.6 数字4旋转识别结果

▲ 图数字5旋转

▲ 图1.2.7 数字5旋转识别结果

▲ 图数字6旋转

▲ 图1.2.8 数字6旋转识别结果

▲ 图数字7旋转

▲ 图1.2.10 数字7旋转识别结果

▲ 图数字8旋转

▲ 图1.2.12 数字8旋转识别结果

▲ 图数字9旋转

▲ 图1.2.13 数字9旋转识别结果

※ 旋转总结 ※

测试了七段数字图片段角度对于识别的影响。可以看到对于6,9两个数字，在旋转过程中他们之间会相互转换。2,5在旋转180°之后，它们与自己相同，会出现两个识别相同。0,8与其他数字自检有着比较多的差异。 1,7两个数字有着较强的交叉。

■ 相关文献链接:

模型扫描识别图片
对于七段数码数字模型进行改进：一个关键的数字1的问题

● 相关图表链接:

图1.1.1 用于旋转测试的图片
图1.1.2 旋转后的结果
图数字旋转
图数字0旋转
图1.2.1 数字0旋转输出结果
图数字1旋转
图1.2.2 数字1旋转识别结果
图数字2旋转
图1.2.3 数字2旋转识别结果
图数字3旋转
图1.2.4 数字3旋转识别结果
图数字4旋转
图1.2.6 数字4旋转识别结果
图数字5旋转
图1.2.7 数字5旋转识别结果
图数字6旋转
图1.2.8 数字6旋转识别结果
图数字7旋转
图1.2.10 数字7旋转识别结果
图数字8旋转
图1.2.12 数字8旋转识别结果
图数字9旋转
图1.2.13 数字9旋转识别结果

模型识别数字

▲ 图2.1 识别数字

from headm import *                 # =import paddle
import paddle.fluid as fluid
import cv2
import cv2imgwidth = 48
imgheight = 48
inputchannel = 1
kernelsize   = 5
targetsize = 10
ftwidth = ((imgwidth-kernelsize+1)//2-kernelsize+1)//2
ftheight = ((imgheight-kernelsize+1)//2-kernelsize+1)//2class lenet(paddle.nn.Layer):def __init__(self, ):super(lenet, self).__init__()self.conv1 = paddle.nn.Conv2D(in_channels=inputchannel, out_channels=6, kernel_size=kernelsize, stride=1, padding=0)self.conv2 = paddle.nn.Conv2D(in_channels=6, out_channels=16, kernel_size=kernelsize, stride=1, padding=0)self.mp1    = paddle.nn.MaxPool2D(kernel_size=2, stride=2)self.mp2    = paddle.nn.MaxPool2D(kernel_size=2, stride=2)self.L1     = paddle.nn.Linear(in_features=ftwidth*ftheight*16, out_features=120)self.L2     = paddle.nn.Linear(in_features=120, out_features=86)self.L3     = paddle.nn.Linear(in_features=86, out_features=targetsize)def forward(self, x):x = self.conv1(x)x = paddle.nn.functional.relu(x)x = self.mp1(x)x = self.conv2(x)x = paddle.nn.functional.relu(x)x = self.mp2(x)x = paddle.flatten(x, start_axis=1, stop_axis=-1)x = self.L1(x)x = paddle.nn.functional.relu(x)x = self.L2(x)x = paddle.nn.functional.relu(x)x = self.L3(x)return xmodel = lenet()
model.set_state_dict(paddle.load('/home/aistudio/work/seg7model4_1_all.pdparams'))cutdir = '/home/aistudio/work/7seg/rotate/cutdir'
rotateangle = range(0, 360, 10)def modelpre(n, degree):fn = os.path.join(cutdir, '%d_%03d.BMP'%(n, degree))img = cv2.imread(fn)data = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)data = data - mean(data)stdd = std(data)data = data/stddinputs = data[newaxis, :, :]preid = model(paddle.to_tensor([inputs], dtype='float32'))return preid.numpy()outdim = []for r in rotateangle:out = modelpre(9, r)outdim.append(out[0])plt.clf()
plt.figure(figsize=(10,6))
for i in range(10):plt.plot([a[i] for a in outdim], label='Out=%d'%i)plt.xlabel("Angle")
plt.ylabel("Value")
plt.grid(True)
plt.tight_layout()
plt.legend(loc='upper right')
plt.savefig('/home/aistudio/stdout.jpg')
plt.show()imgfile = '/home/aistudio/work/7seg/rotate/220113000554.JPG'
OUT_SIZE    = 48
def pic2netinput(imgfile):img = cv2.imread(imgfile)gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)imgwidth = gray.shape[1]imgheight = gray.shape[0]f = os.path.basename(imgfile)numstr = '1234'numnum = len(numstr)imgarray = []labeldim = []for i in range(numnum):left = imgwidth * i // numnumright = imgwidth * (i + 1) // numnumdata = gray[0:imgheight, left:right]dataout = cv2.resize(data, (OUT_SIZE, OUT_SIZE))dataout = dataout - mean(dataout)stdd = std(dataout)dataout = dataout / stddif numstr[i].isdigit():imgarray.append(dataout[newaxis,:,:])labeldim.append(int(numstr[i]))test_i = paddle.to_tensor(imgarray, dtype='float32')test_label = array(labeldim)test_l = paddle.to_tensor(test_label[:, newaxis], dtype='int64')return test_i, test_ldef checkimglabel(imgfile):inp, label = pic2netinput(imgfile)preout = model(inp)preid = paddle.argmax(preout, axis=1).numpy().flatten()label = label.numpy().flatten()error = where(label != preid)[0]printt(preid:, label:)checkimglabel(imgfile)

图片旋转对于识别模式带来的变化相关推荐

旋转图片验证码（识别/破解）解决（一）
旋转图片验证码防御能力到底有多高.人机校验现巨大漏洞?旋转图片验证码(识别/破解)解决(一) 旋转图片验证码,一个为防止爬虫攻击的行为验证产品.它是由最初的字符验证码演变而来,与其相似的产品还有滑动拼 ...
android 实现图片旋转，移动，缩放，并且记录变化值，用另外一张图片显示出来
最近公司要做一个戒指试戴的功能,就是把戒指通过手势移动到你指定的手指处,并且保存状态,方便下次进入时显示,可以参考APP"钻石快线"的试戴功能, 图片网上有很多的教程教你怎么把图片 ...
MVP模式的Android 调用系统拍照，相册，剪裁，适配到7.0,修复拍照图片旋转问题
Android 调用系统拍照,相册,剪裁,适配到7.0,修复拍照图片旋转问题直接上代码首先添加拍照需要的权限 <uses-permission android:name="andr ...
IE下及标准浏览器下的图片旋转（二）—— Canvas（1）
文章过长,一篇无法保存. IE下及标准浏览器下的图片旋转(一)--滤镜,CSS3 3. canvas canvas 是html5中的新标签,使用canvas之前我们先看下它的定义:<canvas ...
可折叠Web可能会给我们带来的变化
简介:可折叠Web即将到来,我们应该去思考可折叠Web可能会给我们带来什么变化,如果这一天真的到来,我们的技术能否支持该设备? 作者 | 大漠可折叠Web的说法是可折叠设备带来的.可折叠设备形式多样 ...
flex 图片旋转（解决公转和自转问题）
在Flex中图片的旋转是既有公转和自转的.这样在图片旋转的时候就有一定小麻烦: 为了更好地说明问题,先引入两个概念:"自转"和"公转".想象一下,地球在绕着太阳 ...
计算机对农业领域带来的变革,智慧农业将给农业带来哪些变化？
原标题:智慧农业将给农业带来哪些变化? 一.什么是智慧农业? 智慧农业是指充分应用信息技术成果,集成应用计算机与网络技术.物联网技术.音视频技术.3S技术.无线通信技术及专家智慧与知识实现农业可视化远 ...
聊聊安卓折叠屏给交互设计和开发带来的变化
很多年前,前端同学都觉得PC端的适配(兼容处理)难,都认为移动端的时代适配会容易得多,也无需考虑那么多的事情.事实并非如此,移动端的时代同样面临着各种适配的处理.特别是刘海机的出现,前端需要考虑刘海机 ...
体验QQ2011Beta3带来的变化和惊喜
体验QQ2011Beta3带来的变化和惊喜<?xml:namespace prefix = o ns = "urn:schemas-microsoft-com:office:offic ...

图片旋转对于识别模式带来的变化

§01 旋转图片

1.1 旋转图片

1.1.1 分割形成旋转图片

（1）分割代码

（2）分割旋转结果

1.2 模型识别结果

1.2.1 网络识别代码

1.2.2 绘制结果

※ 旋转总结 ※

模型识别数字

图片旋转对于识别模式带来的变化相关推荐

最新文章

热门文章