| Model Type | Text Detection & Recognition |
|---|---|
| Framework | AI Edge LiteRT, OpenVINO |
| Algorithm | EAST+ CRNN |
| Technical Details | Uses an EAST text detector with a CRNN recognition stage to locate and transcribe text from images on edge devices. |
Scene Text Detection – Light Model
Detects and recognizes text in images using a lightweight OCR pipeline optimized for edge devices.
Leave your message here
Fill the form with the required information
$0.00
Scene Text Detection – Light Model
app details
Resources
Use Cases
Quality Control
Performance Benchmark
Hardware · Backend
Processing unit
Latency (ms)
Avg. Peak RAM
Intel Tiger Lake · OpenVINO
GPU
14.6 ms
685.9 MB
Intel Tiger Lake · OpenVINO
CPU
44.5 ms
685.5 MB
Intel Tiger Lake · AiEdgeLiteRT
CPU
165.5 ms
83.5 MB
NXP i.MX 8M Plus · AiEdgeLiteRT
NPU
30978.3 ms
80.1 MB
NXP i.MX 8M Plus · AiEdgeLiteRT
GPU
30978.3 ms
76.1 MB
NXP i.MX 8M Plus · AiEdgeLiteRT
CPU
2309.5 ms
76.1 MB
Qualcomm QCS6490 · AiEdgeLiteRT
NPU
629.1 ms
79.6 MB
Qualcomm QCS6490 · AiEdgeLiteRT
CPU
621.5 ms
82.5 MB
MediaTek Genio 510 · AiEdgeLiteRT
CPU
534.3 ms
75.9 MB
Scene Text Detection – High Accuracy
Detects and recognizes text in complex real-world images using a high-accuracy OCR pipeline for edge applications.
View Model
Object Detection – YOLOX
Detects and locates multiple object categories in images and video streams using the lightweight YOLOX architecture.
View Model
Image Classification
Real-time image classification for recognizing visual categories on edge devices.
View Model|
|