Chinese word and sentence image recognition system
Patent Information
- Authority / Receiving Office
- TW · TW
- Patent Type
- Utility models
- Current Assignee / Owner
- BOXIANG TECH CO LTD
- Filing Date
- 2026-02-26
- Publication Date
- 2026-08-01
Smart Images

Figure TWG2TB001904438_001 
Figure TWG2TB001904438_002 
Figure TWG2TB001904438_003
Abstract
Claims
1. A Chinese word and sentence image recognition system, comprising: An image capturing unit is configured to capture an image and generate an image signal having at least one Chinese word or phrase; and a processing unit is electrically connected to the image capturing unit and has a learning model, wherein the processing unit receives the image signal from the image capturing unit, identifies the image signal and generates a plurality of black dot features, and the learning model generates at least one word or phrase recognition result.
2. The Chinese word and phrase image recognition system as described in claim 1 further includes a storage unit electrically connected to the processing unit, and the storage unit stores the word and phrase recognition results.
3. The Chinese word and phrase image recognition system as described in claim 1 further includes an input interface electrically connected to the image capturing unit and the processing unit, and the input interface is used to control the image capturing unit to capture images and the processing unit to recognize the image signal.
4. The Chinese word and phrase image recognition system as described in claim 1 further includes a power unit that provides operating power to the processing unit, storage unit, and input unit.
5. The Chinese word and phrase image recognition system as described in claim 1, wherein the processing unit identifies the image signal and generates at least one character frame via the Chinese words and phrases.
6. The Chinese word and phrase image recognition system as described in claim 5, wherein the processing unit defines a scaled image via the string frame.
7. The Chinese word and phrase image recognition system as described in claim 6, wherein the processing unit defines a plurality of feature grids within the scaled image, and the processing unit obtains the number of black dot features via the feature grids.
8. The Chinese word and phrase image recognition system as described in claim 7, wherein the processing unit divides the height of the scaled image into three blocks on an average basis, and converts the three blocks into three projected histograms by vertical projection, and the processing unit obtains the number of black dot features through the projected histograms.
9. The Chinese word and phrase image recognition system of claim 8, wherein the processing unit calculates the number of black dots in the feature grid and the projected histogram, the number of black dots including black dot density and black dot ratio.