Image Layout Apparatus Face Region Decision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image layout methods fail to appropriately position faces in images, especially in group photos, which can distort the atmosphere of the original photography, and do not effectively utilize varying background image insertion regions of different sizes and shapes.
Innovation Solution
An image layout apparatus and method that decides display regions based on the number of faces and their distances within images, using face detection to determine appropriate regions for layout, and generates a layout image by extracting and arranging these regions on a background image, considering the sizes and shapes of insertion regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If each person in group photos is normalized and trimmed to the same size, then the album can be generated to look fine with uniform faces, but the atmosphere at the time of photography is greatly ruined
Solution Approach 1:
The patent applies local quality by treating images with single faces differently from group photos. For single-face images, normalization and trimming are applied to achieve uniform appearance. For group photos, the entire image is preserved without normalization to maintain the original photographic atmosphere. This differentiated approach allows each type of image to be processed according to its specific characteristics rather than applying a uniform rule to all images.
2Manufacturing precision
If face regions are extracted and resized to predetermined sizes, then faces can be positioned at predetermined positions in identification photographs, but the natural composition and atmosphere of ordinary photography images are lost
Solution Approach 1:
The system applies different processing strategies based on the type of image. For identification photographs where precise positioning is required, face extraction and resizing is applied. For ordinary photography images where atmospheric preservation is important, the entire image is used without extraction or resizing. This localized application of processing rules resolves the contradiction by adapting the level of intervention to the specific requirements of each image type.
3Object-generated harmful factors
If the entirety of each image is used as display region, then the original atmosphere is preserved, but images with multiple faces do not utilize the background image insertion regions of various sizes and shapes effectively
Solution Approach 1:
The patent implements local quality by making the display region selection dependent on the specific characteristics of each image and its corresponding insertion region. For single-face images, the display region is adjusted to match the insertion region's size and shape, achieving effective utilization. For group photos, the entire image is used as the display region to preserve atmosphere, even if it doesn't perfectly match the insertion region. This context-dependent approach resolves the contradiction by allowing flexibility in different situations.
Data Source
AI summary
A user decides images to be laid out on one image. For each image showing presence of face among the decided images, a region decision means decides a display region including at least one face in the corresponding image, according to the number of faces therein and according to a distance between the faces in the case where the number of the faces is larger than 1. A layout image generation unit extracts the display regions from the respective images, and generates a layout image by laying out the extracted display regions on a background image.