Design of Hardware Accelerator Structure on FPGA for Real-Time Image Classification through Optimised Convolution Layer
Bibliographic record
Abstract
Deep learning models, especially CNNs, are essential in a range of key applications within AI, but they face challenges regarding computational requirements, memory limitations, and latency when deployed on resource-constrained devices. Field Programmable Gate Arrays (FPGAs) offer a beneficial alternative because of their reconfigurability, efficiency, and parallel processing abilities. This paper presents a design of a hardware Accelerator Structure on an FPGA for Real-Time Image Classification Through an optimised convolution Layer (ASFRIC) model designed to facilitate real-time AI inference in embedded systems. The use of transfer learning on VGG architectures for high classification accuracy, 8-bit quantisation to improve efficiency, and a specialised backpropagation method for better learning on hardware accelerators. An engineered convolution accelerator to overcome memory limitations, relying on loop unrolling and tiling for performance improvement. A SoC-FPGA with the Xilinx Vitis AI toolchain, the ASFRIC model shows improved performance in accuracy, execution speed, and energy efficiency when compared to conventional CPU and GPU solutions. To assess the model's effectiveness, key metrics such as confidence matrix, accuracy, precision, recall, and loss are performed for evaluation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".