• Urvashi Dubey
• Amar Nayak
• Rajesh Boghey

Human life is important and many of researchers are working to develop better diagnosis models. Pulmonary disease infection are increasing hence easy detection and prediction algorithms are in demand. This paper has proposed a model TFFPDP that classify the input medical image (X-Ray) into infected and non-infected class. In order to increase the detection accuracy this work has utilized co-occurrence matrix model that extract texture feature from the image. Further Discrete Wavelet Transform model was used that extract frequency feature form the image. Both features were used for the training of convolutional neural network. Experiment was done on real dataset images and result shows that proposed model has improved the detection accuracy by 2.126% as compared to existing model of pulmonary disease detection.Further it was found that use of CNN model has increases the work f-measure value by 2.82% as compared to LFA-RNN .

Pulmonary Disease, Image Processing, Information Extraction, Visual Processing,Machine Learning.

"Texture and Frequency Based Medical Image Pulmonary Disease Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 12, page no.f742-f749, December-2023, Available :http://www.jetir.org/papers/JETIR2312590.pdf

"Texture and Frequency Based Medical Image Pulmonary Disease Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 12, page no. ppf742-f749, December-2023, Available at : http://www.jetir.org/papers/JETIR2312590.pdf