Weak hypothesis generation apparatus and method, learning apparatus and method, detection apparatus and method, facial expression learning apparatus and method, facial expression recognition apparatus and method, and robot apparatus

A learning apparatus for learning data to be used by a detection apparatus, the detection apparatus being adapted for judging whether provided data is a detection target or not by using a data set including plural learning samples each of which has been labeled as a detection target or non-detection target, the learning apparatus comprising:

• one or more programmable central processing units;
• and
• a computer-readable storage medium encoded with instructions executable by at least one of the central processing units and operatively coupled to at least one or the central processing units, the instructions comprising
• instructions that comprise a weak hypothesis selection unit for repeating processing to select one weak hypothesis from plural weak hypotheses for estimating whether provided data is a detection target or not,
• instructions that comprise a reliability calculation unit for, every time a weak hypothesis is selected by the weak hypothesis selection unit, calculating reliability of the weak hypothesis on the basis of the result of estimation of the selected weak hypothesis with respect to the data set, and
• instructions that comprise a threshold value learning unit for calculating and adding the product of the result of estimation of the weak hypothesis with respect to the data set and the reliability of the weak hypothesis every time a weak hypothesis is selected by the weak hypothesis selection unit and learning an abort threshold value for aborting the processing by the detection apparatus to judge whether the provided data is a detection target or not on the basis of the result of the addition.

A learning method for learning data to be used by a detection apparatus, the detection apparatus being adapted for judging whether provided data is a detection target or not by using a data set including plural learning samples each of which has been labeled as a detection target or non-detection target, the learning method being performed by an apparatus that comprises one or more programmable central processing units and a computer-readable storage medium that is operatively coupled to at least one of the central processing units and is encoded with instructions capable of being executed by at least one of the central processing units, the method comprising:

• at least one of the central processing units executing instructions, retrieved from the computer-readable storage medium, that cause the central processing unit to perform a weak hypothesis selection step of repeating processing to select one weak hypothesis from plural weak hypotheses for estimating whether provided data is a detection target or not;
• at least one of the central processing units executing instructions, retrieved from the computer-readable storage medium, that cause the central processing unit to perform a reliability calculation step of, every time a weak hypothesis is selected at the weak hypothesis selection step, calculating reliability of the weak hypothesis on the basis of the result of estimation of the selected weak hypothesis with respect to the data set;
• and
• at least one of the central processing units executing instructions, retrieved from the computer-readable storage medium, that cause the central processing unit to perform a threshold value learning step of calculating and adding the product of the result of estimation of the weak hypothesis with respect to the data set and the reliability of the weak hypothesis every time a weak hypothesis is selected at the weak hypothesis selection step, and learning an abort threshold value for aborting the processing by the detection apparatus to judge whether the provided data is a detection target or not on the basis of the result of the addition.