A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCR
Automatic information extraction from identity documents remains a challenging task due to variations in image quality, document layout, and text appearance. This study proposes a key information extraction system for the Peruvian National Identity Document (DNI) by integrating object detection and...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | inglés |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881700515822174208 |
|---|---|
| author | Jhoselyn Noemi Quispe Valero Fredy Abel Huanca Torres |
| author_browse | Fredy Abel Huanca Torres Jhoselyn Noemi Quispe Valero |
| author_facet | Jhoselyn Noemi Quispe Valero Fredy Abel Huanca Torres |
| author_sort | Jhoselyn Noemi Quispe Valero |
| collection | Producción científica |
| description | Automatic information extraction from identity documents remains a challenging task due to variations in image quality, document layout, and text appearance. This study proposes a key information extraction system for the Peruvian National Identity Document (DNI) by integrating object detection and Transformer-based text inference into a unified processing pipeline. The proposed approach combines YOLO11 for the detection and segmentation of regions of interest (ROI) and TrOCR for inferring the textual content of each identified field. The system was trained and evaluated using multiple document fields, including document number, given names, surnames, date of birth, and sex. Experimental results indicate consistent performance in both detection and text inference tasks, even without incorporating explicit preprocessing or post-processing stages. In particular, the fine-tuning process applied to TrOCR improved the recognition of compound names and Spanish-specific characters, including accented vowels and the letter ñ. The achieved performance was comparable to and, in some cases, surpassed that reported in related studies under equivalent evaluation metrics. Furthermore, the proposed methodology was integrated into a functional web-based application, enabling validation of the complete extractionworkflowand the structured organization of the inferred information. Overall, the findings support the feasibility of the proposed system for automatic information extraction from identity documents under real-world conditions. |
| format | Article |
| id | openalex:W7202367362 |
| institution | UPeU |
| language | English |
| publishDate | 2026 |
| publishDateRange | 2026 |
| publishDateSort | 2026 |
| record_format | dspace |
| spelling | openalex:W7202367362A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCRJhoselyn Noemi Quispe ValeroFredy Abel Huanca TorresYOLOv11TrOCRoptical character recognitionregion of interest detectiondocument segmentationfine-tuningweb applicationHandwritten Text Recognition TechniquesVehicle License Plate RecognitionAdvanced Neural Network ApplicationsAutomatic information extraction from identity documents remains a challenging task due to variations in image quality, document layout, and text appearance. This study proposes a key information extraction system for the Peruvian National Identity Document (DNI) by integrating object detection and Transformer-based text inference into a unified processing pipeline. The proposed approach combines YOLO11 for the detection and segmentation of regions of interest (ROI) and TrOCR for inferring the textual content of each identified field. The system was trained and evaluated using multiple document fields, including document number, given names, surnames, date of birth, and sex. Experimental results indicate consistent performance in both detection and text inference tasks, even without incorporating explicit preprocessing or post-processing stages. In particular, the fine-tuning process applied to TrOCR improved the recognition of compound names and Spanish-specific characters, including accented vowels and the letter ñ. The achieved performance was comparable to and, in some cases, surpassed that reported in related studies under equivalent evaluation metrics. Furthermore, the proposed methodology was integrated into a functional web-based application, enabling validation of the complete extractionworkflowand the structured organization of the inferred information. Overall, the findings support the feasibility of the proposed system for automatic information extraction from identity documents under real-world conditions.Articlehttps://doi.org/10.1109/access.2026.3723416W7202367362enIEEE Access2169-35362026-01-01 |
| spellingShingle | YOLOv11 TrOCR optical character recognition region of interest detection document segmentation fine-tuning web application Handwritten Text Recognition Techniques Vehicle License Plate Recognition Advanced Neural Network Applications Jhoselyn Noemi Quispe Valero Fredy Abel Huanca Torres A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCR |
| title | A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCR |
| title_full | A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCR |
| title_fullStr | A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCR |
| title_full_unstemmed | A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCR |
| title_short | A Key Information Extraction Model for the Peruvian National Identity Document Using YOLO and TrOCR |
| title_sort | key information extraction model for the peruvian national identity document using yolo and trocr |
| topic | YOLOv11 TrOCR optical character recognition region of interest detection document segmentation fine-tuning web application Handwritten Text Recognition Techniques Vehicle License Plate Recognition Advanced Neural Network Applications |
| topic_facet | YOLOv11 TrOCR optical character recognition region of interest detection document segmentation fine-tuning web application Handwritten Text Recognition Techniques Vehicle License Plate Recognition Advanced Neural Network Applications |
| url | https://doi.org/10.1109/access.2026.3723416 |
| work_keys_str_mv | AT jhoselynnoemiquispevalero akeyinformationextractionmodelfortheperuviannationalidentitydocumentusingyoloandtrocr AT fredyabelhuancatorres akeyinformationextractionmodelfortheperuviannationalidentitydocumentusingyoloandtrocr AT jhoselynnoemiquispevalero keyinformationextractionmodelfortheperuviannationalidentitydocumentusingyoloandtrocr AT fredyabelhuancatorres keyinformationextractionmodelfortheperuviannationalidentitydocumentusingyoloandtrocr |