Image caption generation is a significant area of study in artificial intelligence and computer vision, focusing on training systems to generate accurate textual descriptions of images. This paper presents an advanced framework for image captioning using a dataset sourced from Kaggle. The process begins with pre-processing techniques, including the Flexiframe Filter, which dynamically adjusts the window size based on local variance to reduce noise in both text and images. Bright- Contrast augmentation is then applied to enhance input images, enriching the dataset and improving feature extraction. The encoder module utilises a Sinusoidal Spatial Transform Convolutional Neural Network (SST-CNN) integrated with a Visual Geometry Group (VGG16) model for feature extraction and encoding. For the decoder, stochastic k-sampling is combined with a Dense Neural Network and a Gated Recurrent Unit (GRU) to generate initial captions. To refine these captions, a fine-tuned Bidirectional Encoder Representations from Transformers (BERT) model is employed for enhanced coherence and accuracy. The model's performance is evaluated using standard metrics, achieving BLEU-1, METEOR, ROUGE-L, and CIDER scores of 1, 0.99, 0.99, and 1, respectively. The proposed approach demonstrates significant improvements in generating descriptive and accurate image captions, making it a robust solution for applications requiring semantic understanding of visual data.