Systems and methods for automated extraction of measurement information in medical videos
Systems and methods providing automated extraction of information contained in video data and uses thereof are described. In particular, systems and associated methods are described that provide techniques for extracting data embedded in video, for example measurement-value pairs of medical videos, for use in a variety of applications, for example video indexing, searching and decision support applications.
1. A computer program product for providing one or more video data applications comprising:
a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to access one or more frames of video data;
computer readable program code configured to preprocess said one or more frames of video data to produce one or more preprocessed frames;
computer readable program code configured to extract embedded characters from said one or more preprocessed frames;
computer readable program code configured to utilize said embedded characters extracted from said one or more preprocessed frames for one or more of a decision support application and an automated archive storage application; and
computer readable program code configured to create a feature vector characterizing said one or more frames of video data using said embedded characters;
wherein said decision support application further comprises retrieving one or more medical videos having a feature vector similar to said feature vector characterizing said one or more frames of video data; and
wherein said one or more medical videos having a feature vector similar to said feature vector characterizing said one or more frames of video data are identified using collaborative filtering.
2. The computer program product according to claim 1 , wherein said video data comprises medical video data and further wherein said embedded characters comprise one or more feature value-pairs.
3. The computer program product according to claim 1 , wherein to preprocess said one or more frames further comprises removing one or more non-embedded character features from said one or more frames prior to conducting optical character recognition.
4. The computer program product according to claim 3 , wherein to extract embedded characters from said one or more preprocessed frames further comprises conducting optical character recognition with said one or more preprocessed frames as input.
5. The computer program product according to claim 4 , wherein to extract embedded characters from said one or more preprocessed frames further comprises extracting name-value pairs from said one or more preprocessed frames and conducting a table analysis using one or more templates.
6. The computer program product according to claim 1 , wherein automated archive storage application further comprises determining a storage policy for one or more medical videos based on said embedded characters.
7. A system providing one or more video data applications comprising:
one or more processors; and
a memory operatively connected to the one or more processors;
wherein, responsive to execution of computer readable program code accessible to the one or more processors, the one or more processors are configured to:
access one or more frames of video data;
preprocess said one or more frames of video data to produce one or more preprocessed frames;
extract embedded characters from said one or more preprocessed frames; and
utilize said embedded characters extracted from said one or more preprocessed frames for one or more of a decision support application and an automated archive storage application;
wherein the decision support application is configured to identify and retrieve one or more videos comprising at least one feature bearing similarity relative to said one or more frames of video data; and
wherein the identifying comprises employing collaborative filtering.
8. The system according to claim 7 , wherein said video data comprises medical video data and further wherein said embedded characters comprise one or more feature value-pairs.
9. A computer program product for providing one or more video data applications comprising:
a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to access one or more frames of video data;
computer readable program code configured to preprocess said one or more frames of video data to produce one or more preprocessed frames;
computer readable program code configured to extract embedded characters from said one or more preprocessed frames; and
computer readable program code configured to utilize said embedded characters extracted from said one or more preprocessed frames for one or more of a decision support application and an automated archive storage application;
wherein the decision support application is configured to identify and retrieve one or more videos comprising at least one feature bearing similarity relative to said one or more frames of video data; and
wherein the identifying comprises employing collaborative filtering.