Data recognition model construction apparatus and method for constructing data recognition model thereof, and data recognition apparatus and method for recognizing data thereof
Disclosed is a data recognition model construction apparatus. The data recognition model construction apparatus includes a video inputter configured to receive a video, an image composition unit configured to, based on a common area included in each of a plurality of images that form at least a portion of the video, generate a composition image by overlaying at least a portion of the plurality of images, a learning data inputter configured to receive the generated composition image, a model learning unit configured to make a data recognition model learn using the generated composition image, and a model storage configured to store the learnt data recognition model.
1. A data recognition model construction apparatus comprising:
a video inputter configured to receive a video;
an image composition unit configured to obtain at least one common object included in each of a plurality of images that form at least a portion of the video, and obtain a composition image by overlaying a plurality of common areas corresponding to the at least one common object with each other, each of the plurality of common areas being included in a corresponding image among the plurality of images and including the at least one common object, and each of the plurality of images including a common area and a background;
a model learning unit configured to make a data recognition model learn using the obtained composition image; and
a model storage configured to store the learnt data recognition model,
wherein the image composition unit is further configured to, based on an attribute of the background, selectively perform either a first operation of overlaying only the plurality of common areas or a second operation of overlaying the plurality of common areas and a plurality of backgrounds corresponding to the plurality of common areas, the first operation or the second operation being selected based on the attribute of the background.
2. The apparatus as claimed in claim 1 , wherein the attribute of the background includes relevance between the common area and the background, and a ratio of an area corresponding to the background in the plurality of images.
3. The apparatus as claimed in claim 2 , wherein the image composition unit is further configured to:
based on the relevance between the common area and the background being greater than a first predetermined value, perform the second operation of overlaying the plurality of common areas and the plurality of backgrounds corresponding to the plurality of common areas,
based on the relevance between the common area and the background being less than the first predetermined value, perform the first operation of overlaying only the plurality of common areas.
4. The apparatus as claimed in claim 2 , wherein the image composition unit is further configured to:
based on the ratio of the area corresponding to the background in the plurality of images being greater than a second predetermined value, perform the first operation of overlaying only the plurality of common areas,
based on the ratio of the area corresponding to the background in the plurality of images being less than the second predetermined value, perform the second operation of overlaying the plurality of common areas and the plurality of backgrounds corresponding to the plurality of common areas.
5. The apparatus as claimed in claim 1 , wherein the model learning unit further configured to obtain learning data comprising the composition image and a classification result corresponding to the composition image, the model learning unit being further configured to make a data recognition model learn using the obtained composition image and the classification result.
6. A method for constructing a data recognition model by a data recognition model construction apparatus, the method comprising:
receiving a video;
obtaining at least one common object included in each of a plurality of images that form at least a portion of the video;
obtaining a composition image by overlaying a plurality of common areas corresponding to the at least one common object with each other, each of the plurality of common areas being included in a corresponding image among the plurality of images and including the at least one common object, and each of the plurality of images including a common area and a background;
learning a data recognition model using the obtained composition image; and
storing the learnt data recognition model,
wherein the obtaining the composition image comprises, based on an attribute of the background, selectively performing either a first operation of overlaying only the plurality of common areas or a second operation of overlaying the plurality of common areas and a plurality of backgrounds corresponding to the plurality of common areas, the first operation or the second operation being selected based on the attribute of the background.
7. The method as claimed in claim 6 , wherein the attribute of the background includes relevance between the common area and the background, and a ratio of an area corresponding to the background in the plurality of images.
8. The method as claimed in claim 6 , wherein the obtaining the composition image comprises:
based on the relevance between the common area and the background being greater than a first predetermined value, performing the second operation of overlaying the plurality of common areas and the plurality of backgrounds corresponding to the plurality of common areas,
based on the relevance between the common area and the background being less than the first predetermined value, performing the first operation of overlaying only the plurality of common areas.