Neural And Heuristic Copy Space Detection for Media Overlay Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for identifying copy space in images and video frames are time-consuming and inefficient, especially when dealing with large volumes of data, and do not accurately account for areas suitable for overlaying media content without obscuring important visual elements.
Innovation Solution
A neural networks-based system and a heuristics-based system for detecting copy space, which utilize bounding boxes to automatically identify areas in images and video frames suitable for overlaying media content, using trained neural networks and image processing techniques to determine optimal placement and orientation of media elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual marking of copy space is performed, then accuracy in identifying suitable areas is improved, but time consumption increases significantly
Solution Approach 1:
The patent replaces the manual mechanical marking process with an automated neural network-based system. The neural network analyzes image features and automatically identifies copy space regions, eliminating the need for manual curator intervention while maintaining high accuracy through learned patterns from training data.
Solution Approach 2:
The system enables self-service by allowing the neural network to autonomously perform copy space detection without human assistance. The model processes images independently, identifying suitable regions for media overlay based on its trained understanding of visual content and spatial relationships.
2Productivity
If automated detection methods are used, then productivity is improved, but measurement precision may deteriorate
Solution Approach 1:
The neural network is trained in advance on large datasets of images with annotated copy space regions. This preliminary training phase enables the model to learn effective detection patterns, which are then applied during automated processing to maintain high accuracy while achieving fast processing speeds.
Solution Approach 2:
The system incorporates feedback mechanisms where the neural network's predictions are evaluated against ground truth data during training, and where detection results can be refined through iterative optimization. This feedback loop ensures that automated detection maintains high precision while improving processing efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed herein are system, method, and computer readable storage medium for detecting space suitable for overlaying media content onto an image using (i) a neural networks-based approach and (ii) using a heuristics-based approach. The system receives a candidate image which may be an image or a video frame. In the neural networks-based approach, the candidate image is then input into a neural network. The neural network may output coordinates and one or more dimensions representing one or more bounding boxes for inserting media content into the candidate image. In the heuristics-based approach, the candidate image is processed using image processing techniques in order to automatically propose spaces that are further analyzed using a heuristic rules-based approach to select insertion spaces defined by bounding boxes for inserting media content. Subsequently, one or more media content items may be selected for insertion onto the selected bounding boxes in the image. The system may then cause a display of the image with the selected media content item overlaid onto the image within the selected bounding boxes.