Information processing device, information processing method and program

An information processing device comprising:

• a change point detection unit which detects change points of a moving image;
• a transition detection unit which detects transition of a subject included in a plurality of images configuring the moving image included between two adjacent change points among the detected change points;
• a composition similarity degree information generation unit which generates composition similarity degree information indicating similarity degrees between compositions of the plurality of images and a composition of a specific scene, based on feature amounts of the compositions of the plurality of images configuring the moving image included between the two adjacent change points;
• a voice similarity degree information generation unit which generates voice similarity degree information indicating a similarity degree between voice data associated with the moving image and voice data of the specific scene, based on a feature amount of the voice data associated with the moving image included between the two adjacent change points;
• a determination unit which determines whether or not the moving image included between the two adjacent change points is a moving image corresponding to the specific scene, based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information;
• and
• a display control unit which performs control such that the moving image included between the two adjacent changes points which is determined as the moving image corresponding to the specific scene is displayed on a display unit, based on a determination result of the determination unit,
• wherein the determination unit includes:
• an evaluation value generation unit which generates an evaluation value for evaluating the moving image included between the two adjacent change points, based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information;
• and
• an evaluation value determination unit which compares the evaluation value with a threshold value and performs the determination based on a comparison result.

An information processing method comprising:

• detecting change points of a moving image;
• detecting transition of a subject included in a plurality of images configuring the moving image included between two adjacent change points among the detected change points;
• generating composition similarity degree information indicating similarity degrees between compositions of the plurality of images and a composition of a specific scene, based on feature amounts of the compositions of the plurality of images configuring the moving image included between the two adjacent change points;
• generating voice similarity degree information indicating a similarity degree between voice data associated with the moving image and voice data of the specific scene, based on a feature amount of the voice data associated with the moving image included between the two adjacent change points;
• determining whether or not the moving image included between the two adjacent change points is a moving image corresponding to the specific scene, based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information;
• and
• setting the moving image included between the two adjacent change points which is determined as the moving image corresponding to the specific scene as a specific moving image and applying priority of the specific moving image to the specific moving image based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information.

A non-transitory computer-readable storage medium having stored thereon, a computer program having at least one code section for image processing, the at least one code section being executable by a computer for causing the computer to perform steps comprising:

• detecting change points of a moving image;
• detecting transition of a subject included in a plurality of images configuring the moving image included between two adjacent change points among the detected change points;
• generating composition similarity degree information indicating similarity degrees between compositions of the plurality of images and a composition of a specific scene, based on feature amounts of the compositions of the plurality of images configuring the moving image included between the two adjacent change points;
• generating voice similarity degree information indicating a similarity degree between voice data associated with the moving image and voice data of the specific scene, based on a feature amount of the voice data associated with the moving image included between the two adjacent change points;
• determining whether or not the moving image included between the two adjacent change points is a moving image corresponding to the specific scene, based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information;
• and
• setting the moving image included between the two adjacent change points which is determined as the moving image corresponding to the specific scene as a specific moving image and applying priority of the specific moving image to the specific moving image based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information.

An information processing device comprising:

• a change point detection unit which detects change points of a moving image;
• a transition detection unit which detects transition of a subject included in a plurality of images configuring the moving image included between two adjacent change points among the detected change points;
• a composition similarity degree information generation unit which generates composition similarity degree information indicating similarity degrees between compositions of the plurality of images and a composition of a specific scene, based on feature amounts of the compositions of the plurality of images configuring the moving image included between the two adjacent change points;
• a voice similarity degree information generation unit which generates voice similarity degree information indicating a similarity degree between voice data associated with the moving image and voice data of the specific scene, based on a feature amount of the voice data associated with the moving image included between the two adjacent change points;
• a determination unit which determines whether or not the moving image included between the two adjacent change points is a moving image corresponding to the specific scene, based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information;
• and
• a priority applying unit which sets the moving image included between the two adjacent change points which is determined as the moving image corresponding to the specific scene as a specific moving image and applies priority of the specific moving image to the specific moving image based on the detected transition, the generated composition similarity degree information and the generated voice similarity degree information.