Out of every 135,000 used tires purchased, only 8,000 make it to the final stage to be made reusable [1]. The cost for purchasing, handling, transporting as well as inspection by experts results in heavy losses accrued which demotivates both individuals as well as organisations from adopting such recycling strategies. Here we propose a solution which will help reduce the cost as well make the process efficient and time saving. For identifying reusable truck tires effectively and prevent discarding of completely fine tires, deep learning is used to realise the image recognition of good and scrap truck tires. Firstly, Shearography Tire testing is done in the production laboratory or on the test track. Vacuum chamber measuring system helps- in taking multiple pictures of tires. Then image enhancement and data preprocessing are used to augment images, then these were input into the network for training. Afterwards, for reaching a higher accuracy, the learning rate and iteration numbers were adjusted frequently, and early stopping was added to prevent over-fitting. Finally, the experimental results show an accuracy of 99.784. Therefore, the recognition algorithm based on deep learning can help in fast and secure inspection also with semi-skilled operators. Further, the knowledge obtained can be used to improve the algorithm itself which is not possible with multiple experts inspecting the tires at different locations. Inspection and evaluation can work in parallel and can provide used truck tires their second life by an industry leading, highly automated tire recycling process and contribute to the company’s focus on sustainability, circular economy, and environmental responsibility. This will keep the materials of the tires in use cycle as long as possible giving them further lives with help of retreading and other processes.