OCR技术浅析-自写篇(2)

本例仅以本人浅薄理解,妄想自制文字识别程序,实际在识别部分未有完善。

<?php
class readChar{
    private $imgSize;        //图片尺寸
    private $imgGd2;        //图像转GD2
    private $Index=array();    //颜色索引(key即为颜色索引)
    private $bigColor;        //二维图像颜色值(存储索引)
    function __construct($imgPath){
        $this->imgSize=getimagesize($imgPath);
        $this->imgSize['size']=$this->imgSize[0]*$this->imgSize[1];
        $this->imgGd2=imagecreatefromstring(file_get_contents($imgPath));
        if (imageistruecolor($this->imgGd2)) {
            imagetruecolortopalette($this->imgGd2, false, 256);//真彩图片转换为调色板
        }
        $this->setGray();
    }
    function __destruct(){
        imagedestroy($this->imgGd2);
    }
    private function showImg(){
        foreach($this->Index as $k=>$v){
                imagecolorset($this->imgGd2,$k,$v,$v,$v);
        }
        header('Content-type: image/jpg');
        imagejpeg($this->imgGd2);
        exit;
    }
    private function setGray(){
        /*
            灰度化
            RGB均值/RGB单值/最大/最小/人性化:0.3R+0.59G+0.11B
            bug:若灰度值相等的两个颜色,刚好是主要颜色 则会识别不出来
        */
        for($i=ImageColorstotal($this->imgGd2)-1;$i>=0;$i--){
            $rgb=ImageColorsForIndex($this->imgGd2,$i);
            $this->Index[$i]=(int)(($rgb['red']+$rgb['green']+$rgb['blue'])/3);    //imagecolorset改变索引颜色
        }
        $this->bigColor=array();
        $pro=array();            //各灰度值占比
        for($x=0;$x<$this->imgSize[0];$x++){
            $this->bigColor[$x]=array();
            for($y=0;$y<$this->imgSize[1];$y++){
                $Index=ImageColorAt($this->imgGd2, $x, $y);
                $this->bigColor[$x][$y]=$Index;
                $pro[$this->Index[$Index]]=@$pro[$this->Index[$Index]]+1;
            }
        }
        array_walk($pro,function(&$v){$v=$v/$this->imgSize['size'];});
        $this->setTwo($pro);
        
    }
    private function setTwo($pro){
        /*
            二值化 T很重要
            以T为阈值,低于T的为白否则为黑
            双峰法
            迭代法:
            OSTU(大津法):不懂
                前景和背景的分割阈值记作T,前景像素点数占比为ω0,平均灰度μ0;背景像素点数占比例ω1,平均灰度为μ1。
                总平均灰度记为μ
                类间方差记假设图像的背景较暗,并且图像的大小为M×N,灰度值小于阈值T的像素数为N0,大于阈值T的像素数为N1
                则有:
              ω0=N0/ M×N (1)
              ω1=N1/ M×N (2)
              N0+N1=M×N (3)
              ω0+ω1=1    (4)
              μ=ω0*μ0+ω1*μ1 (5)
                    g=ω0(μ0-μ)^2+ω1(μ1-μ)^2 (6)    
                将式(5)代入式(6),得到等价公式: g=ω0ω1(μ0-μ1)^2 
                类间方差g最大时的阈值T,即为所求
            P分位法:需已知目标占图像的比例,以不同灰度值进行分割若比例≈P 则T为该灰度值
        */
        $T=127;
        $g_max=0;
        for ($i=0;$i<256;$i++){
            $w0 = $w1 = $u0_temp = $u1_temp = $u0 = $u1 = $g_tmp = 0;
            for ($j=0;$j<256;$j++){
                if ($j <= $i){   //背景部分  
                    $w0 += @$pro[$j];
                    $u0_temp += $j * @$pro[$j];
                }else{            //前景部分  
                    $w1 += @$pro[$j];
                    $u1_temp += $j * @$pro[$j];
                }
            }
            $u0 = $w0==0?0:$u0_temp / $w0;
            $u1 = $w1==0?0:$u1_temp / $w1;
            $g_tmp =$w0 *$w1* pow(($u0 - $u1), 2);//类间方差 g=w0*w1*(u0-u1)^2
            if ($g_tmp > $g_max){
                $g_max = $g_tmp;
                $T = $i;
            }
        }
        for($x=0;$x<$this->imgSize[0];$x++){
            for($y=0;$y<$this->imgSize[1];$y++){
                $index = $this->bigColor[$x][$y];
                if($this->Index[$index]<=$T){
                    $this->Index[$index]=0;
                }else{
                    $this->Index[$index]=255;
                }
            }
        }
        $this->avgFilter();
    }
    private function avgFilter(){
        /*
        代码不实现
        均值滤波器、自适应维纳滤波器、中值滤波器、形态学噪声滤除器、小波去噪
        滤波前对于图片边界:不处理/填充0 or 255/填充临近灰度值
    */
        return $this->getChar();
        
    }
    private function getChar(){
        /*
            拆字
        */
        $pointTotal=array();    //Y轴统计
        for($x=0;$x<$this->imgSize[0];$x++){
            for($y=0;$y<$this->imgSize[1];$y++){
                @$pointTotal[$y]+=$this->Index[$this->bigColor[$x][$y]]>0?0:1;
            }
        }
        $chars=array(); //Y轴划线
        $prev = $pointTotal[0];
        $tmpLine=array();
        foreach($pointTotal as $k=>$v){
            if($v==0 && $prev!=0){
                //imageline ($this->imgGd2,0,$k,$this->imgSize[0]-1,$k,0);//划线 对程序无用
                $tmpLine[]=$k;
            }elseif($v!=0 && $prev==0){
                //imageline ($this->imgGd2,0,$k-1,$this->imgSize[0]-1,$k,0);//划线 对程序无用
                $tmpLine[]=$k-1;
            }
            $prev=$v;
            if(count($tmpLine)==2){
                $chars[]=$tmpLine;
                $tmpLine=array();
            }
        }
        if(!$chars){
            //imageline ($this->imgGd2,0,0,$this->imgSize[0]-1,0,0);//划线 对程序无用
            //imageline ($this->imgGd2,0,$this->imgSize[1]-1,$this->imgSize[0]-1,$this->imgSize[1]-1,0);//划线 对程序无用
            $chars []=array(0,$this->imgSize[1]-1);
        }
        foreach($chars as $line=>$ypoint){
            $pointTotal=array();//每行的X轴统计
            for($x=0;$x<$this->imgSize[0];$x++){
                $pointTotal[$x]=0;
                for($y=$ypoint[0];$y<=$ypoint[1];$y++){
                    $pointTotal[$x]+=$this->Index[$this->bigColor[$x][$y]]>0?0:1;
                }
            }
            $xLine=array();
            $tmpLine=array();//每行X轴划线
            $prev = $pointTotal[0];
            foreach($pointTotal as $k=>$v){
                if($v==0 && $prev!=0){
                    //imageline ($this->imgGd2,$k,$ypoint[0],$k,$ypoint[1],0);//划线 对程序无用
                    $tmpLine[]=$k-1;
                }
                if($v!=0 && $prev==0){
                    //imageline ($this->imgGd2,$k-1,$ypoint[0],$k-1,$ypoint[1],0);//划线 对程序无用
                    $tmpLine[]=$k;
                }
                if(count($tmpLine)==2){
                    $xLine[]=$tmpLine;
                    $tmpLine=array();
                }
                $prev=$v;
            }
            foreach($xLine as $k=>$v){
                $v['xcode']=$v['ycode']=array();
                for($x=$v[0];$x<=$v[1];$x++){
                    for($y=$ypoint[0];$y<=$ypoint[1];$y++){
                        $gry = $this->Index[$this->bigColor[$x][$y]]>0?0:1;
                        @$v['xcode'][$x-$v[0]]        +=$gry;
                        @$v['ycode'][$y-$ypoint[0]]    +=$gry;
                    }
                }
                $xLine[$k]=$v;
            }
            $chars[$line]['xline']=$xLine;
        }
        $this->bigColor=null;
        foreach($chars as $v){
            foreach($v['xline'] as $vv){
                $this->tranChar($vv['xcode'],$vv['ycode']);
            }
        }
    }
    private function tranChar($myX,$myY){
        /*
            识别文字
            本例用到的php自带函数 similar_text
            通过把每个字x和y轴做映射,然后和模板做相似度匹配(模板图为50x50所以需将映射做压缩处理)
        */
        $tplx='0,0,0,0,0,0,0,0,12,22,30,34,23,16,13,11,10,8,8,8,8,8,8,6,6,6,6,8,8,7,8,9,10,10,12,14,20,34,30,26,16,0,0,0,0,0,0,0,0,0';
        $tply='9,14,17,15,11,10,10,8,8,8,9,8,8,7,8,8,7,8,7,8,8,8,8,8,8,8,8,8,8,8,8,7,8,7,8,8,7,8,8,8,8,9,8,9,10,12,15,17,13,9';
        $diff=count($myX)-count($myY);
        $middle = (int)(abs($diff)/2);
        if($diff<0){
            $minMy=&$myX;
        }else{
            $minMy=&$myY;
        }
        for($i=0;$i<abs($diff);$i++){
            if($i<$middle){
                array_unshift($minMy,0);
                continue;
            }
            array_push($minMy,0);
        }
        $ratio = 50/count($myX);
        $newX=array();
        $newY=array();
        foreach($myX as $k=>$v){
            $key = min(ceil($k*$ratio),49);
            is_array(@$newX[$key]) || $newX[$key]=array();
            is_array(@$newY[$key]) || $newY[$key]=array();
            $newX[$key][]=$myX[$k];
            $newY[$key][]=$myY[$k];
        }
        array_walk($newY,function(&$v){$v=round(array_sum($v)/count($v));});
        array_walk($newX,function(&$v){$v=round(array_sum($v)/count($v));});
        
        $sx=similar_text(implode(',',$newX),$tplx);
        $sy=similar_text(implode(',',$newY),$tply);
        echo 'X:'.$sx.'/'.strlen($tplx).'='.($sx/strlen($tplx));
        echo "<br>";
        echo 'Y:'.$sy.'/'.strlen($tply).'='.($sy/strlen($tply));
        exit;
    }
}
new readChar("imgurl.jpg");

 

附上模板图片:

 

 

posted @ 2018-08-17 16:21  寻觅~~  阅读(246)  评论(0编辑  收藏  举报