This chapter proposes a new and innovative method of smart optical character recognition (OCR) for translation (SOT) from an English image to Bangla and Hindi language. For translation, this OCR system can take any picture from any documents which contain printed English sentences. SOT can translate the image into text within two languages. The translated text from SOT can also be copied and kept for further use. SOT can convert the full image in a text format and then can translate some of the portions of an image by cropping. Google translator has been used here for the OCR. This API can translate the image into a printed text or a machine-encoded text. But the translated text cannot be kept for further use which is an immense disparity between SOT and Google translator. Moreover, many APIs also deploy, which can translate the image into a text format but cannot ferry the limit of copying text which is collected after translating text from the image. SOT can be beneficiary among all the OCR as it struck the limit of copying text.