General-AI Platform for Multi-Angle Image Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current AI technologies, such as Convolutional Neural Networks, require large numbers of training samples, extensive computing power, and long training times, limiting their ability to generalize from small data sets and perform tasks outside their specific training domains, while also being inefficient in terms of cost, resource usage, and flexibility.
Innovation Solution
The development of a General-AI platform using Z-numbers and fuzzy logic concepts, which allows for computation with uncertain information and smaller training samples, enabling efficient image recognition and pattern recognition from any direction, and enabling continuous learning and recognition without the need for retraining from scratch.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Convolutional Neural Networks are used for image recognition, then recognition accuracy is improved, but training time and computing power requirements increase significantly
Solution Approach 1:
The patent segments the image recognition task into multiple views by rotating the input image to generate different perspectives. Each view is processed independently through the neural network, and results are aggregated. This segmentation allows the system to achieve comprehensive recognition accuracy while reducing the complexity and training time required for any single view processing.
Solution Approach 2:
The patent introduces a temporal dimension by processing images at multiple rotation angles (0°, 45°, 90°, 135°, etc.) and aggregating results over time. This dimensional transformation allows the system to achieve 3D object recognition from 2D images without requiring exponentially more training data or computing power for a single comprehensive model.
2Adaptability or versatility
If Convolutional Neural Networks are trained to recognize objects from multiple angles, then adaptability is improved, but the system requires retraining from scratch for new object classes
Solution Approach 1:
The patent creates a universal image recognition system that processes images from any rotation angle using the same neural network architecture. By rotating input images to multiple standard views and aggregating results, the system achieves multi-angle recognition capability without requiring separate specialized models for each angle, thereby reducing retraining complexity when adding new object classes.
3Reliability
If large numbers of training samples are used to improve generalization, then recognition reliability is improved, but resource consumption and cost increase
Solution Approach 1:
The patent performs preliminary image rotation and augmentation during the training phase to generate multiple views from limited training samples. By pre-processing training images to include various rotation angles, the system improves generalization capability to recognize objects from unseen angles without requiring proportionally larger training datasets.
Data Source
AI summary
Specification covers new algorithms, methods, and systems for: Artificial Intelligence; the first application of General-AI. (versus Specific, Vertical, or Narrow-AI) (as humans can do) (which also includes Explainable-AI or XAI); addition of reasoning, inference, and cognitive layers/engines to learning module/engine/layer; soft computing; Information Principle; Stratification; Incremental Enlargement Principle; deep-level/detailed recognition, e.g., image recognition (e.g., for action, gesture, emotion, expression, biometrics, fingerprint, tilted or partial-face, OCR, relationship, position, pattern, and object); Big Data analytics; machine learning; crowd-sourcing; classification; clustering; SVM; similarity measures; Enhanced Boltzmann Machines; Enhanced Convolutional Neural Networks; optimization; search engine; ranking; semantic web; context analysis; question-answering system; soft, fuzzy, or un-sharp boundaries/impreciseness/ambiguities/fuzziness in class or set, e.g., for language analysis; Natural Language Processing (NLP); Computing-with-Words (CWW); parsing; machine translation; music, sound, speech, or speaker recognition; video search and analysis (e.g., “intelligent tracking”, with detailed recognition); image annotation; image or color correction; data reliability; Z-Number; Z-Web; Z-Factor; rules engine; playing games; control system; autonomous vehicles or drones; self-diagnosis and self-repair robots; system diagnosis; medical diagnosis/images; genetics; drug discovery; biomedicine; data mining; event prediction; financial forecasting (e.g., for stocks); economics; risk assessment; fraud detection (e.g., for cryptocurrency); e-mail management; database management; indexing and join operation; memory management; data compression; event-centric social network; social behavior; drone/satellite vision/navigation; smart city/home/appliances/IoT; and Image Ad and Referral Networks, for e-commerce, e.g., 3D shoe recognition, from any view angle.