Volume - 13 | Issue-1
Volume - 13 | Issue-1
Volume - 13 | Issue-1
Volume - 13 | Issue-1
Volume - 13 | Issue-1
Aim: To perform an automated image caption generator using a convolutional neural network compared with Long Short-Term Memory. Material and Methods: Automated Image caption generator performed using convolutional neural network (N=10) and long short term memory (N=10) with the split size of training and testing dataset 70% and 30% using G-power setting parameters:(α=0.05 and power=0.85) respectively. Results: (CNN) convolutional neural network (94%) as the better accuracy compared to long short term memory accuracy(78%) and attained the significance value 0.651 (Two-tailed, p>0.05). Conclusion: convolutional neural network achieved significantly better classification than Long Short Term Memory for generating a description of the image.