Breaking Language Barriers with Image Detection and Natural Language Processing Model for English to Spanish Translation

This research proposes an advanced approach that integrates multiple image detection techniques and natural language processing (NLP) methodologies for English-to-Spanish language translation. The developed software accepts an image as input, which undergoes preprocessing using adaptive thresholding, morphological transformations, and edge detection algorithms such as Canny and Sobel operators to enhance text clarity. Text detection and localization are achieved using the EfficientDet and EAST (Efficient and Accurate Scene Text) detector frameworks, followed by Optical Character Recognition (OCR) using PyTesseract, a wrapper for Google’s Tesseract OCR. The detected text is passed to an NLP system for translation, which employs a sequence-to-sequence transformer model implemented with Keras, TensorFlow, and NumPy. Additional techniques, such as Byte Pair Encoding (BPE) for text tokenization and positional encoding for transformer-based attention, improve translation efficiency. An English-Spanish dictionary from Anki and a large parallel corpus dataset were used for training. The NLP pipeline leverages semantic analysis, part-of-speech tagging, and dependency parsing to preserve grammatical structure and context. Fine-tuning the transformer model parameters, including learning rate scheduling and gradient clipping, further optimized system performance. The research demonstrates a 93.7% translation accuracy, achieved by combining state-of-theart image processing algorithms, advanced transformer architectures, and a robust training dataset. This hybrid approach significantly improves the accuracy of English-to-Spanish translations, validating the effectiveness of integrating computer vision and NLP technologies.