Object Identification Using Saliency and Index Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object identification methods in electronic devices are user-input dependent and prone to errors, especially when using saliency maps, as they require sophisticated user interaction and may not accurately reflect the desired object's outline information.
Innovation Solution
An electronic device with a processor that outputs content, receives user input to specify a point, determines a search region, generates a saliency map based on this region, and identifies the region of interest using both the saliency map and an index map to accurately pinpoint the desired object with minimal user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If user-input based technique is used for object identification, then object can be identified, but the method requires excessive user interaction and is highly affected by sophistication of user input
Solution Approach 1:
The system performs self-service by automatically generating saliency maps and identifying objects without requiring user input for region selection. The processor autonomously analyzes the image, generates saliency information, and identifies objects based on predefined criteria, eliminating the need for users to manually specify regions or draw boundaries.
Solution Approach 2:
The system performs preliminary action by pre-generating saliency maps and identifying potential object regions before user interaction. The processor analyzes the entire image in advance, creates saliency information highlighting probable object locations, and prepares candidate regions for identification, reducing the complexity of subsequent user operations.
2Measurement precision
If saliency map technique is used for object identification, then object can be identified, but the outline information of the object may not be accurately reflected
Solution Approach 1:
The system merges multiple identification approaches by combining saliency map-based identification with contour-based identification. The processor generates both saliency information for locating objects and contour information for defining object boundaries, then integrates these two types of information to achieve accurate object identification with precise outline representation.
Solution Approach 2:
The system uses composite information by combining different types of data representations - saliency maps that highlight probable object locations and contour maps that define precise object boundaries. This composite approach leverages the strengths of both methods: saliency for location and contour for accurate shape definition.
3Measurement precision
If user must select region or draw closed curve for object identification in still image, then object can be identified, but the process requires excessive user input and interaction
Solution Approach 1:
The system performs self-service by automatically generating saliency maps and identifying objects without requiring user input for region selection. The processor autonomously analyzes the image, generates saliency information, and identifies objects based on predefined criteria, eliminating the need for users to manually specify regions or draw boundaries.
4Adaptability or versatility
If the entire region of content is analyzed for object identification, then all objects can be detected, but the processing time and complexity increase
Solution Approach 1:
The system applies segmentation by dividing the image processing task into distinct stages: first generating saliency information to identify probable object regions, then using this segmented information to guide further analysis. This segmentation allows the system to focus computational resources on relevant regions rather than analyzing the entire image uniformly.
Solution Approach 2:
The system performs preliminary action by pre-generating saliency maps that highlight probable object locations before detailed analysis. This preliminary step creates a filtered view of the image, allowing subsequent processing to focus only on regions of interest rather than analyzing the entire image in detail.
Data Source
AI summary
An electronic device includes a display, and a processor functionally connected with the display. The processor is configured to output content including one or more objects through the display, receive user input for specifying at least one point in the entire region of the content, determine a portion of an entire region with respect to the at least one point as a search region, obtain a saliency map associated with the content based on the search region, and determine a region of interest of the user based on the saliency map. Alternatively, the processor is configured to obtain an index map associated with the content by dividing the entire region of the content into similar regions according to a preset criterion and determine the region of interest of the user by overlapping the saliency map and the index map. It is possible to provide other embodiments.