Apparatus and method for image recognition

• US 7,054,489 B2
• Filed: 10/02/2003
• Issued: 05/30/2006
• Est. Priority Date: 09/30/1999
• Status: Expired due to Fees

• Current Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Yamaoka, Megumi, Nagao, Kenji
• Primary Examiner(s): Wu, Jingge
• Assistant Examiner(s): KIM, CHONG R
• Application Number:
  US10/677,866
• Publication Number:
  US 20040062435A1
• Time in Patent Office: 971 Days
• Field of Search: 382/203, 382/190
• US Class Current: 382/203
• CPC Class Codes: G06V 10/443 by matching or filtering

Abstract

An object recognizing apparatus is provided which is capable of precisely recognizing an object in an input image with the use of a corresponding learning image even when a local-segment of the input image coincides with a learning-local-segment of another similar learning image. The apparatus comprises (1) image dividing means for dividing an input image, which is received from image input means, into local-segments, (2) similar-local-segment extracting means for extracting a similar learning-local-segment to the local-segment of the input image from a learning image database, (3) object position estimating means for estimating the position of an object to be identified in the input image from the coordinates of the local-segment and the coordinates of the learning-local-segment corresponding to the local-segment, (4) counting means for counting the local-segments coincide with their corresponding learning-local-segments, and (5) object determining means for judging that the object to be identified is present when a result of counting is greater than a predetermined number. Consequently, the object and its position in any input image can be detected at higher accuracy.

Claims

1. An image recognizing apparatus for detecting a shape of an object from an image, comprising:

an image database storing a shape identifier and images of objects as model images corresponding to the shape identifier, each of the objects having a same shape, the shape identifier including information for representing the shape of each of the objects and position information for indicating a oortion of a shaoe segment in the shape;

model generating means for calculating a base vector in a feature space from pixel values of model image segments each of which is provided by dividing each of the model images, for projecting the model image segments in the feature space as model image segment vectors, for calculating statistic values from the model image segment vectors, each of the model image segments having a same shape segment, and for adding the shape identifier to feature statistic values to provide a feature shape parameter;

a shape database for storing the base vector and the feature shape parameter;

an image input unit for supplying an input image;

an image cutout unit for cutting out the input image to provide input-image segments;

shape classifying means operable to

project the input-image segments in the feature space to provide input-image segment vectors based on the base vector, respectively,

compare the input-image segment vectors with the model image segment vectors using the feature shape parameter to estimate overall areas which the object occupies in the input image from position information included in the shape identifiers of respective model image segment vectors most similar to the input-image segment vectors,

count a number of times an area out of the estimated overall areas is estimated, and

determine that the object having the shape is present at the area in the input image if the number is greater than a predetermined value so as to output the area as a position of the object having the shape; and

an output unit for releasing data indicating the shape of the object and the position of the object in the input image if the object having the shape is present in the input image.

2. The image recognizing apparatus according to claim 1, wherein said model generating means is operative to calculate the feature shape parameter from an average vector and a covariance matrix of the model image segment vectors.

3. The image recognizing apparatus according to claim 1, wherein said model generating means is operative to calculate an average image of the model image segments for the shape segment, to calculate the base vector from a pixel value of the average image, to project the model image segments in the feature space as the model image segment vectors, and to add the shape identifier to the model image segment vectors.