Automatic recognition method for measurement point in cephalo image

An automatic measurement point recognition system comprising an arithmetic processor capable of automatically recognizing a measurement point in a cephalometric image, and a database, wherein

• the database stores:
• information of a plurality of control images showing peripheral partial regions different from one another that have been predetermined with respect to a feature point of interest, and
• a deep learning model trained to learn positions of the feature point in the peripheral partial regions, and
• the arithmetic processor comprises:
• a peripheral partial region detecting unit that detects, from a cephalometric image acquired from a subject, a plurality of peripheral partial regions that match the control images,
• a feature point position estimating unit that estimates a candidate position of the feature point in each of the peripheral partial regions using the deep learning model, and
• a most likely position determining unit that determines a most likely estimated position of the feature point in the cephalometric image based on the distribution of the candidate positions estimated, and determines that the most likely estimated position is the position of the measurement point,
• wherein when the distribution density of the candidate positions shows at least two or more peaks and when any two candidate positions estimated as most likely positions from the tops of the respective peaks are distant from each other by a predetermined threshold value or a greater distance, the most likely position determining unit determines that the two candidate positions are separate measurement points with respect to the feature point.