Avaliação de OCR Embarcado para Dispositivos Móveis: Desempenho, Privacidade e Usabilidade
Resumo
Este estudo apresenta uma análise comparativa entre três tecnologias de OCR para dispositivos móveis: Vision OCR, MLKit Mobile e Tesseract Mobile. Foram utilizados 848 exemplos reais de palavras extraídas de ambientes urbanos, e as ferramentas foram avaliadas com e sem a aplicação de técnicas de pré-processamento. As métricas utilizadas possibilitaram uma avaliação completa do desempenho de cada solução. Os resultados mostram que o Vision OCR apresenta o melhor desempenho, seguido pelo MLKit e pelo Tesseract com pré-processamento otimizado. Também foram analisados aspectos de segurança (processamento no dispositivo), usabilidade (facilidade de operação, instalação e documentação, considerando o tamanho dos arquivos em ambientes embarcados) e facilidade de integração. As soluções nativas oferecem desempenho superior com menor necessidade de ajustes, enquanto o Tesseract, apesar de exigir um pipeline mais sofisticado, garante privacidade máxima por ser de código aberto e controlado pelo desenvolvedor.Referências
B. Chatpaitoon and R. Itthipanichpong, “Effect of optical text recognition (ocr) and text-to-speech (tts) smartphone app on vision-related quality of life in visually impaired people.” Investigative Ophthalmology & Visual Science, vol. 64, no. 8, pp. 2808–2808, 2023.
S. Kompalli, S. Nayak, S. Setlur, and V. Govindaraju, “Challenges in ocr of devanagari documents,” in Eighth International Conference on Document Analysis and Recognition (ICDAR’05). IEEE, 2005, pp. 327–331.
M. Laine and O. S. Nevalainen, “A standalone ocr system for mobile cameraphones,” in 2006 IEEE 17th international symposium on personal, indoor and mobile radio communications. IEEE, 2006, pp. 1–5.
Apple Inc., “Vision Framework - Apple Developer Documentation,” 2024, acessado em: 30 de julho de 2025. [Online]. Available: [link]
Google Developers, “ML Kit — Google for Developers,” 2024, acessado em: 30 de julho de 2025. [Online]. Available: [link]
R. Smith, “An overview of the tesseract ocr engine,” in Ninth international conference on document analysis and recognition (ICDAR 2007), vol. 2. IEEE, 2007, pp. 629–633.
S. Badla, “Improving the efficiency of tesseract ocr engine,” 2014.
Y. Wang, Y. Liu, T. Wu, and I. Duncan, “A cost-effective ocr implementation to prevent phishing on mobile platforms,” in 2020 International Conference on Cyber Security and Protection of Digital Services (Cyber Security). IEEE, 2020, pp. 1–8.
T. Mantoro, A. M. Sobri, and W. Usino, “Optical character recognition (ocr) performance in server-based mobile environment,” in 2013 International Conference on Advanced Computer Science Applications and Technologies. IEEE, 2013, pp. 423–428.
L. V. da Silva, P. L. J. D. Junior, and S. S. da Costa Botelho, “An optical character recognition post-processing method for technical documents,” in Conference on Graphics, Patterns and Images (SIBGRAPI). SBC, 2023, pp. 126–131.
I. L. Correa, P. L. J. Drews, and R. N. Rodrigues, “Combination of optical character recognition engines for documents containing sparse text and alphanumeric codes,” in 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE, 2021, pp. 299–306.
Mindee, “doctr: Document text recognition,” [link], 2021.
A. Malkadi, M. Alahmadi, and S. Haiduc, “A study on the accuracy of ocr engines for source code transcription from programming screencasts,” in Proceedings of the 17th International Conference on Mining Software Repositories, 2020, pp. 65–75.
A. P. Tafti, A. Baghaie, M. Assefi, H. R. Arabnia, Z. Yu, and P. Peissig, “Ocr as a service: an experimental evaluation of google docs ocr, tesseract, abbyy finereader, and transym,” in International Symposium on Visual Computing. Springer, 2016, pp. 735–746.
K. Thammarak, P. Kongkla, Y. Sirisathitkul, and S. Intakosum, “Comparative analysis of tesseract and google cloud vision for thai vehicle registration certificate,” International Journal of Electrical and Computer Engineering, vol. 12, no. 2, pp. 1849–1858, 2022.
R. Kaur and D. V. Sharma, “Punjabi text recognition system for portable devices: A comparative performance analysis of cloud vision api with tesseract,” Journal of Computer Science and Engineering (JCSE), vol. 2, no. 2, pp. 104–111, 2021.
L. R. Mursari and A. Wibowo, “The effectiveness of image preprocessing on digital handwritten scripts recognition with the implementation of ocr tesseract,” Computer Engineering and Applications Journal, vol. 10, no. 3, pp. 177–186, 2021.
U. Hengaju and B. K. Bal, “Improving the recognition accuracy of tesseract-ocr engine on nepali text images via preprocessing,” Advancement in Image Processing and Pattern Recognition, vol. 3, no. 2, p. 3, 2023.
D. Sporici, E. Cus, nir, and C.-A. Boiangiu, “Improving the accuracy of tesseract 4.0 ocr engine using convolution-based preprocessing,” Symmetry, vol. 12, no. 5, p. 715, 2020.
H. Michalak and K. Okarma, “Improvement of image binarization methods using image preprocessing with local entropy filtering for alphanumerical character recognition purposes,” entropy, vol. 21, no. 6, p. 562, 2019.
A. Franco, “Optical recognition of the philippines’ancient text: A deep learning approach,” INTERNATIONAL JOURNAL, vol. 8, no. 03, 2025.
B. P. Sari, R. W. Sholikah, and R. V. H. Ginardi, “The development of mobile application for object recognition based on deep learning to assist people with visually impaired,” in 2024 2nd International Symposium on Information Technology and Digital Innovation (ISITDI). IEEE, 2024, pp. 222–227.
S. Lucas, A. Panaretos, L. Sosa, A. Tang, S. Wong, and R. Young, “Icdar 2003 robust reading competitions,” in Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings., 2003, pp. 682–687.
J. B. Zimmerman, S. M. Pizer, E. V. Staab, J. R. Perry, W. McCartney, and B. C. Brenton, “An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement,” IEEE Transactions on Medical Imaging, vol. 7, no. 4, pp. 304–312, 1988.
Tesseract OCR, “Data Files — Tesseract OCR,” [link], 2025, acessado em 8 de agosto de 2025.
S. Kompalli, S. Nayak, S. Setlur, and V. Govindaraju, “Challenges in ocr of devanagari documents,” in Eighth International Conference on Document Analysis and Recognition (ICDAR’05). IEEE, 2005, pp. 327–331.
M. Laine and O. S. Nevalainen, “A standalone ocr system for mobile cameraphones,” in 2006 IEEE 17th international symposium on personal, indoor and mobile radio communications. IEEE, 2006, pp. 1–5.
Apple Inc., “Vision Framework - Apple Developer Documentation,” 2024, acessado em: 30 de julho de 2025. [Online]. Available: [link]
Google Developers, “ML Kit — Google for Developers,” 2024, acessado em: 30 de julho de 2025. [Online]. Available: [link]
R. Smith, “An overview of the tesseract ocr engine,” in Ninth international conference on document analysis and recognition (ICDAR 2007), vol. 2. IEEE, 2007, pp. 629–633.
S. Badla, “Improving the efficiency of tesseract ocr engine,” 2014.
Y. Wang, Y. Liu, T. Wu, and I. Duncan, “A cost-effective ocr implementation to prevent phishing on mobile platforms,” in 2020 International Conference on Cyber Security and Protection of Digital Services (Cyber Security). IEEE, 2020, pp. 1–8.
T. Mantoro, A. M. Sobri, and W. Usino, “Optical character recognition (ocr) performance in server-based mobile environment,” in 2013 International Conference on Advanced Computer Science Applications and Technologies. IEEE, 2013, pp. 423–428.
L. V. da Silva, P. L. J. D. Junior, and S. S. da Costa Botelho, “An optical character recognition post-processing method for technical documents,” in Conference on Graphics, Patterns and Images (SIBGRAPI). SBC, 2023, pp. 126–131.
I. L. Correa, P. L. J. Drews, and R. N. Rodrigues, “Combination of optical character recognition engines for documents containing sparse text and alphanumeric codes,” in 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE, 2021, pp. 299–306.
Mindee, “doctr: Document text recognition,” [link], 2021.
A. Malkadi, M. Alahmadi, and S. Haiduc, “A study on the accuracy of ocr engines for source code transcription from programming screencasts,” in Proceedings of the 17th International Conference on Mining Software Repositories, 2020, pp. 65–75.
A. P. Tafti, A. Baghaie, M. Assefi, H. R. Arabnia, Z. Yu, and P. Peissig, “Ocr as a service: an experimental evaluation of google docs ocr, tesseract, abbyy finereader, and transym,” in International Symposium on Visual Computing. Springer, 2016, pp. 735–746.
K. Thammarak, P. Kongkla, Y. Sirisathitkul, and S. Intakosum, “Comparative analysis of tesseract and google cloud vision for thai vehicle registration certificate,” International Journal of Electrical and Computer Engineering, vol. 12, no. 2, pp. 1849–1858, 2022.
R. Kaur and D. V. Sharma, “Punjabi text recognition system for portable devices: A comparative performance analysis of cloud vision api with tesseract,” Journal of Computer Science and Engineering (JCSE), vol. 2, no. 2, pp. 104–111, 2021.
L. R. Mursari and A. Wibowo, “The effectiveness of image preprocessing on digital handwritten scripts recognition with the implementation of ocr tesseract,” Computer Engineering and Applications Journal, vol. 10, no. 3, pp. 177–186, 2021.
U. Hengaju and B. K. Bal, “Improving the recognition accuracy of tesseract-ocr engine on nepali text images via preprocessing,” Advancement in Image Processing and Pattern Recognition, vol. 3, no. 2, p. 3, 2023.
D. Sporici, E. Cus, nir, and C.-A. Boiangiu, “Improving the accuracy of tesseract 4.0 ocr engine using convolution-based preprocessing,” Symmetry, vol. 12, no. 5, p. 715, 2020.
H. Michalak and K. Okarma, “Improvement of image binarization methods using image preprocessing with local entropy filtering for alphanumerical character recognition purposes,” entropy, vol. 21, no. 6, p. 562, 2019.
A. Franco, “Optical recognition of the philippines’ancient text: A deep learning approach,” INTERNATIONAL JOURNAL, vol. 8, no. 03, 2025.
B. P. Sari, R. W. Sholikah, and R. V. H. Ginardi, “The development of mobile application for object recognition based on deep learning to assist people with visually impaired,” in 2024 2nd International Symposium on Information Technology and Digital Innovation (ISITDI). IEEE, 2024, pp. 222–227.
S. Lucas, A. Panaretos, L. Sosa, A. Tang, S. Wong, and R. Young, “Icdar 2003 robust reading competitions,” in Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings., 2003, pp. 682–687.
J. B. Zimmerman, S. M. Pizer, E. V. Staab, J. R. Perry, W. McCartney, and B. C. Brenton, “An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement,” IEEE Transactions on Medical Imaging, vol. 7, no. 4, pp. 304–312, 1988.
Tesseract OCR, “Data Files — Tesseract OCR,” [link], 2025, acessado em 8 de agosto de 2025.
Publicado
30/09/2025
Como Citar
FERNANDES, João Carlos Nepomuceno; GOMES, Francisco Erick Souza; RODRIGUES, Douglas de Araújo; COSTA, Vinícius Lagrota Rodrigues da; REGO, Paulo Antônio Leal; MACEDO, José Antonio Fernandes de; REBOUÇAS FILHO, Pedro Pedrosa.
Avaliação de OCR Embarcado para Dispositivos Móveis: Desempenho, Privacidade e Usabilidade. In: WORKSHOP DE TRABALHOS EM ANDAMENTO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 38. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 174-179.
