1 個回答
- 最新
- 最多得票
- 最多評論
0
Hi Jon,
Thank you for your question.
- If you're looking to detect brand logos that contain a combination of text and logos, we recommend trying Amazon Rekognition Custom Labels.
- Amazon Textract and Custom Labels is a good fit for OCR extraction, for e.g. if your use case is to extract or detect presence of underlying text, in which case, we recommend adding more training samples that are representative of your overall sample set.
Hope this answers your question, and if so, please accept this answer. Have a great day!
已回答 5 個月前
相關內容
- 已提問 6 個月前
- AWS 官方已更新 2 年前
- AWS 官方已更新 1 年前
- AWS 官方已更新 1 年前
Thank you for your suggestions. The logo is pretty much just capitalized text, so in theory textract could be fine for this use case. I'm still confused about why multiple documents from the testing dataset performed clearly differently from the what happened during training. They seemed to have consistent responses, but they don't seem to be consistent with the evaluation that occurred during training. Do you have any potential explanations for why this could be the case?