Image processing for binarization of image data

Abstract

In order to carry out an image processing with high precision by using a simple structure, an image processing apparatus is provided with an input unit, a storage unit, a binarization unit, and a determination unit. The input unit inputs image data of an image. The storage unit stores a first condition on absolute positions of pixels in the image and a second condition on positions of pixels relative to a target pixel. The binarization unit binarizes the target pixel based upon a color data of the target pixel and that of at least one related pixel to the target pixel to generate a binarized value. The at least one related pixel in the image satisfies the first and second conditions. The determination unit determines whether or not the image has a specified pattern, based upon the binarized values.

1 . An image processing apparatus comprising:
 an input unit for inputting image data of an image composed of a plurality of pixels, each having a color data;   a storage unit for storing a plurality of threshold values;   a binarization unit for selecting one of the threshold values stored in the storage unit, and for binarizing the target pixel of the image based upon the selected threshold value; and   a determination unit for determining whether or not the image has a specified pattern, based upon the binarized values obtained by said binarization unit.   
     
     
         2 . The image processing apparatus according to  claim 1 , wherein the binarization unit selects one of the plurality of threshold values based upon the color data of at least one related pixel related to the target pixel among the plurality of pixels. 
     
     
         3 . The image processing apparatus according to  claim 2 , wherein a plurality of pixels within a partial area of the image including the target pixel are at least one related pixels. 
     
     
         4 . The image processing apparatus according to  claim 3 , wherein the binarization unit selects one of the plurality of threshold values based upon the greatest color data among color data possessed by the plurality of related pixels within the partial area. 
     
     
         5 . The image processing apparatus according to  claim 1 , wherein the determination unit determines whether or not an image element having a shape similar to the specified pattern exists, based upon the binarized value, and when the image element is determined to exist, finely examines the shape of the image element to determine whether or not the specified pattern exists. 
     
     
         6 . A nontransitory recording medium for recording an image processing computer program comprising the steps of:
 inputting image data of an image composed of a plurality of pixels, each having a color data;   storing a plurality of threshold values;   selecting one of the threshold values stored, and binarizing the target pixel of the image based upon the selected threshold value; and   determining whether or not the image has a specified pattern based upon the binarized values obtained.   
     
     
         7 . The nontransitory recording medium for recording an image processing computer program according to  claim 6 , wherein the binarizing step selects one of the plurality of threshold values based upon color data of at least one related pixel related to the target pixel among the plurality of pixels. 
     
     
         8 . The nontransitory recording medium for recording an image processing computer program according to  claim 7 , wherein:
 the related pixel corresponds to a plurality of pixels within a partial area of the image including the target pixel and wherein, in the step of binarizing, one of the plurality of threshold values is selected based upon the greatest color data among color data possessed by a plurality of related pixels within the partial area.   
     
     
         9 . An image processing method comprising the steps of;
 inputting image data of an image composed of a plurality of pixels, each having a color data;   storing a plurality of threshold values;   selecting one of the threshold values stored, and binarizing the target pixel of the image based upon the selected threshold value; and   determining whether or not the image has a specified pattern, based upon the binarized values obtained.