Detecting objects in an image being acquired by a digital camera or other electronic image acquisition device

Abstract

The likelihood of a particular type of object, such as a human face, being present within a digital image, and its location in that image, are determined by comparing the image data within defined windows across the image in sequence with two or more sets of data representing features of the particular type of object. The evaluation of each set of features after the first is preferably performed only on data of those windows that pass the evaluation with respect to the first set of features, thereby quickly narrowing potential target windows that contain at least some portion of the object. Correlation scores are preferably calculated by the use of non-linear interpolation techniques in order to obtain a more refined score. Evaluation of the individual windows also preferably includes rotating the feature set data with respect to the image data for the individual windows about another axis.

What is claimed is: 
     
         1 . A method comprising:
 establishing boundaries of a plurality of windows within an image;   for each individual window of the plurality of windows, evaluating data of the image within that individual window with respect to stored data of a set of features of an object, by using a process that includes rotating the stored data with respect to the data of the image about an axis perpendicular to a plane of that individual window; and   assigning scores to the plurality of windows that represent a likelihood of a presence of at least a portion of the object in the plurality of windows.   
     
     
         2 . The method of  claim 1 , wherein said rotating comprises:
 rotating the stored data with respect to the data of the image about an axis perpendicular to a plane of that individual window by changing a parameter of the stored data of the set of features of the object.   
     
     
         3 . The method of  claim 1 , wherein said changing comprises:
 changing the parameter of the stored data of the set of features of the object to a value from a plurality of predetermined parameter values.   
     
     
         4 . The method of  claim 1 , wherein the process further includes:
 switching orientations of the stored data with respect to the data of the image about an axis extending through the object and parallel to the plane to the window.   
     
     
         5 . The method of  claim 4 , wherein said switching comprises:
 sequencing through stored data of sets of features of the object, wherein each set of features represents one orientation of the orientations of the stored data.   
     
     
         6 . The method of  claim 1 , further comprising:
 for each unique pair of one window of the plurality of windows and one feature of the set of features, determining a relationship between a result of said evaluating and a plurality of different thresholds, to determine a plurality of relationships for each of the windows; and   wherein said assigning includes:   assigning scores to the plurality of windows that represent a likelihood of a presence of at least a portion of the object in the plurality of windows, based on the determined relationships for the plurality of windows.   
     
     
         7 . The method of  claim 1 , wherein said assigning scores comprises:
 for each individual window, comparing the result of said evaluating against a first threshold and a second threshold;   if the result is above a higher of the first and second thresholds, assigning a first value to the score;   if the result is below a lower of the first and second thresholds, assigning a second value to the score; and   if the result is between the first and second thresholds, assigning to the score a value interpolated between the first and second values.   
     
     
         8 . A method comprising:
 establishing boundaries of a plurality of windows within an image;   for each individual window of the plurality of windows,
 evaluating data of the image within that individual window with respect to stored data of sets of features of an object, wherein each set of features of the object represents a rotational position of the object with respect to the data of the image about an axis extending through the object and parallel to a plane of that individual window, and 
 selecting a set of feature of the object from the sets of features of the object based on said evaluating; and 
   assigning scores to the plurality of windows that represent a likelihood of a presence of at least a portion of the object in the plurality of windows.   
     
     
         9 . The method of  claim 8 , wherein said evaluating further comprises:
 for each set of features of the object, rotating the stored data with respect to the data of the image about an axis perpendicular to the plane of that individual window.   
     
     
         10 . The method of  claim 8 , wherein said evaluating further comprises:
 for each set of features of the object, rotating the stored data with respect to the data of the image about the axis perpendicular to the plane of that individual window by changing a parameter of the stored data of that set of features of the object.   
     
     
         11 . The method of  claim 10 , further comprising:
 determining a value of the parameter based on said evaluating, among different values of the parameter of the stored data of that set of features of the object.   
     
     
         12 . The method of  claim 8 , wherein said selecting further comprises:
 selecting the set of features of the object that provides a highest likelihood of the presence of at least a portion of the object in that individual window, among the sets of features of the object.   
     
     
         13 . The method of  claim 8 , further comprising:
 for each unique pair of one window of the plurality of windows and one feature of the selected set of features, determining a relationship between a result of said evaluating and a plurality of different thresholds, to determine a plurality of relationships for each of the windows; and   wherein said assigning includes:   assigning scores to the plurality of windows that represent a likelihood of a presence of at least a portion of the object in the plurality of windows, based on the determined relationships for the plurality of windows.   
     
     
         14 . The method of  claim 8 , wherein said assigning scores comprises:
 for each individual window, comparing the result of said evaluating against a first threshold and a second threshold;   if the result is above a higher of the first and second thresholds, assigning a first value to the score;   if the result is below a lower of the first and second thresholds, assigning a second value to the score; and   if the result is between the first and second thresholds, assigning to the score a value interpolated between the first and second values.   
     
     
         15 . An electronic image acquisition device comprising:
 an input interface circuit to receive data of an output of an image sensor, the data representing an image; and   processor circuitry coupled to the input interface circuit to receive the data and to provide processed data of the image, wherein the processor circuitry is configured to detect a likelihood that an object of a particular type is present within the image by performing operations including:
 establishing boundaries of individual windows within the image, 
 evaluating data of the image within individual windows with respect to stored data of a set of features of the particular type of the object by a process that includes rotating the stored data with respect to the data of the image about an axis perpendicular to a plane of a window by changing a parameter of the stored data, and 
 assigning scores to the individual windows that represent a likelihood of a presence of at least a portion of the object in the individual windows. 
   
     
     
         16 . The device of  claim 15 , further comprising said image sensor. 
     
     
         17 . The device of  claim 16 , wherein said image sensor is a two-dimensional image sensor. 
     
     
         18 . The device of  claim 16 , further comprising:
 an optical system that projects an image of an object scene outside of the device onto the sensor.   
     
     
         19 . The device of  claim 15 , wherein the process further includes:
 rotating the stored data with respect to the data of the image about an axis extending through the object and parallel to the plane to the window.   
     
     
         20 . The device of  claim 15 , wherein said operations further include:
 maintaining the stored data of a set of features, for individual ones of a plurality of types of the object, the different object types representing different rotational positions of the object about an axis extending through the object and parallel to the plane to the window, and   wherein rotation of the stored data with respect to the image includes rotating the stored data for individual ones of the plurality of object types with respect to the perpendicular axis.