Electronic apparatus and control method thereof

Patent metadata

Field	Value
Publication number	US-10650283-B2
Application number	US-201815988592-A
Country	US
Kind code	B2
Filing date	May 24, 2018
Priority date	Dec 18, 2017
Publication date	May 12, 2020
Grant date	May 12, 2020

Abstract

An electronic apparatus is provided. The electronic apparatus includes: a storage configured to store a plurality of filters each corresponding to a plurality of image patterns; and a processor configured to classify an image block including a target pixel and a plurality of surrounding pixels into one of the plurality of image patterns based on a relationship between pixels within the image block and to obtain a final image block in which the target pixel is image-processed by applying at least one filter corresponding to the classified image pattern from among the plurality of filters to the image block, wherein the plurality of filters are obtained by learning, through an artificial intelligence algorithm, a relationship between a plurality of first sample image blocks and a plurality of second sample image blocks corresponding to the plurality of first sample image blocks based on each of the plurality of image patterns.

First claim

What is claimed is:

1. An electronic apparatus comprising:
a storage configured to store an index matrix comprising a plurality of index vectors and a plurality of filters corresponding to the plurality of index vectors respectively; and
a processor configured to:
determine whether to transpose an image block based on directivity of the image block including a target pixel and a plurality of surrounding pixels that surround the target pixel,
obtain a gradient vector from the image block or a transposed image block based on the determination, the gradient vector indicating a relationship between the target pixel and the plurality of surrounding pixels that surround the target pixel,
obtain correlations of the image block to the plurality of index vectors respectively based on the gradient vector;
obtain a final image block in which a resolution of the target pixel is enlarged, and wherein the target pixel is image-processed by applying at least one filter from among the plurality of filters to the image block based on the obtained correlations,
wherein the plurality of index vectors respectively represent a plurality of groups in which a plurality of sample gradient vectors obtained from a plurality of first sample image blocks are divided based on a characteristic of each of the plurality of first sample image blocks,
wherein the plurality of filters are obtained by learning a relationship between the plurality of first sample image blocks and a plurality of second sample image blocks corresponding to the plurality of first sample image blocks based on each of the plurality of index vectors.

2. The electronic apparatus as claimed in claim 1 , wherein the processor is configured to determine the gradient vector from the image block when a strength of horizontal directivity of the image block is greater than a strength of vertical directivity of the image block, and to transpose the image block and to determine the gradient vector from the transposed image block when the strength of the horizontal directivity of the image block is less than the strength of the vertical directivity of the image block.

3. The electronic apparatus as claimed in claim 1 , wherein the processor is configured to reduce a size of the gradient vector using an eigen vector stored in the storage and to determine the correlations of the image block to each of the plurality of index vectors based on the gradient vector of which the size is reduced, and
the eigen vector is created by applying a principal component analysis from the plurality of sample gradient vectors.

4. The electronic apparatus as claimed in claim 1 , wherein the processor is configured to determine a first correlation of the image block to each of a plurality of index vector groups based on a first index matrix stored in the storage and the gradient vector, to obtain one of the plurality of index vector groups based on the first correlation, to determine a second correlation of the image block to each of a plurality of index vectors included in the obtained index vector group based on a second index matrix corresponding to the obtained index vector group from among a plurality of second index matrices stored in the storage and the gradient vector, and to obtain the final image block by applying at least one of the plurality of filters to the image block based on the second correlation, wherein:
the plurality of index vector groups are obtained by dividing the plurality of index vectors into a predetermined number of groups,
the first index matrix includes index vectors representing each of the plurality of index vector groups, and
each of the plurality of second index matrices includes a plurality of index vectors corresponding to each of the plurality of index vector groups.

5. The electronic apparatus as claimed in claim 4 , wherein the processor is configured to obtain one of the plurality of index vectors included in the obtained index vector group based on the second correlation, to obtain at least one additional index vector included in the plurality of index vector groups other than the obtained one of the plurality of index vectors and corresponding to the obtained index vector based on similar index vector information stored in the storage, to determine a third correlation of the image block based on the obtained index vector, the obtained additional index vector, and the gradient vector, and to obtain the final image block by applying at least one of the plurality of filters to the image block based the third correlation.

6. The electronic apparatus as claimed in claim 1 , wherein the processor is configured to obtain at least two of the plurality of filters based on a plurality of determined correlations, to determine a final filter based on the at least two filters and correlations corresponding to each of the at least two filters, and to obtain the final image block by applying the determined final filter to the image block.

7. The electronic apparatus as claimed in claim 1 , wherein the plurality of first sample image blocks comprise images in which resolutions of the corresponding second sample image blocks are reduced, and
the processor is configured to obtain the final image block in which the resolution of the target pixel is enlarged by applying at least one of the plurality of filters to the image block.

8. The electronic apparatus as claimed in claim 7 , wherein the processor is configured to obtain an additional image block in which the resolution of the target pixel is enlarged by applying a non-learning-based resolution enlarging technology to the image block, and to update the final image block based on a largest correlation of a plurality of determined correlations and the additional image block.

9. The electronic apparatus as claimed in claim 1 , wherein the electronic apparatus is configured to obtain each of the plurality of filters by obtaining a plurality of first sub-sample image blocks corresponding to one of the plurality of index vectors from among the plurality of first sample image blocks, obtaining a plurality of second sub-sample image blocks corresponding to the plurality of first sub-sample image blocks from among the plurality of second sample image blocks, and learning a relationship between the plurality of first sub-sample image blocks and the plurality of second sub-sample image blocks.

10. A method of controlling an electronic apparatus, comprising:
determining whether to transpose an image block based on directivity of the image block including a target pixel and a plurality of surrounding pixels that surround the target pixel;
obtaining a gradient vector from the image block or a transposed image block based on the determination, the gradient vector indicating a relationship between the target pixel and the plurality of surrounding pixels that surround the target pixel;
obtaining correlations to the image block to a plurality of index vectors included in an index matrix respectively based on the gradient vector; and
obtaining a final image block in which a resolution of the target pixel is enlarged, and wherein the target pixel is image-processed by applying at least one filter from among a plurality of filters to the image block based on the obtained correlations,
wherein the plurality of index vectors respectively represent a plurality of groups in which a plurality of sample gradient vectors obtained from a plurality of first sample image blocks are divided based on a characteristic of each of the plurality of first sample image blocks,
wherein the plurality of filters are obtained by learning a relationship between the plurality of first sample image blocks and a plurality of second sample image blocks corresponding to

Assignees

• Samsung Electronics Co Ltd

Inventors

• Lee Hyun-Seung
• Kim Dong-Hyun
• Moon Young-Su
• Ahn Tae-Gyoung

Classifications

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20024

  Filtering details · CPC title

• G06N3/08

  Learning methods · CPC title

• G06T5/10 Primary

  using non-spatial domain filtering · CPC title

• G06T2207/20081

  Training; Learning · CPC title