Since 1978, in vitro fertilization has been defined as the inability of the couple to conceive for at least one year with timely sexual intercourse without any birth control [2]. The IVF process involves the collection of embryos which are to be inseminated by sperm under clinical conditions. These fertilized embryos are under observation for at least 2 to 5 days. The embryo which is good for implantation will be selected by the embryologists and then it will be transferred to the woman's uterus either on day 2 or day 5. Checking the viability of the embryo is a tedious process that involves experts such as embryologists. physically present. But the success still remains 20 to 25%, due to lack of identification of a potential embryo. To have the possibility of pregnancy, several embryos will be transferred into the woman's uterus. This multiple transfer will be complicated for both the mother and the baby. Several investigators have sought various solutions to clearly identify and transfer a single embryo. Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get an original essay. The overall treatment of IVF depends on the individual cycle response, patient's acceptance ability, clinical aspects, embryo viability and equipment technology. Personal experiences of individuals as patients, clinicians and embryologists. Machine learning techniques can be applied to the IVF process to increase selection efficiency. A model can be designed to evaluate these embryos for the implantation process, which will train with given parameters providing automated decision support to embryologists when needed. Unlike the emergence and importance of decision support systems in the IVF process, the related literature is limited. Artificial neural networks (ANN), convolutional neural networks (CNN), ReLU network classifiers as well as prediction models are used for neural network to achieve accurate results in IVF treatment. Machine learning techniques are prediction models in which the network learns to perform digital image classification or any other task directly from a given set of images, text, or sounds. The medical data obtained will be in text form. Recovering this data becomes complex. Machine learning is typically implemented using neural network architecture. Here in this article, the machine learning model is carried out by training the network through a dataset obtained from multiple hospitals. Once the data is trained, analysis of any image can be achieved very easily. Typically, machine learning networks contain multiple connected layers of convolutional neural networks that can be leveraged on classifiers. Machine learning techniques give better results compared to Hugh transform algorithm and multi-scale vessel filtering. Applying these techniques improved performance by 96.7% and network training is faster than previous algorithms. Recognizing the viability of human embryos from microscopic images is an extremely tedious process, prone to error and subject to intra- and inter-individual unpredictability. Keep in mind: this is just a sample. Get a personalized article from our expert writers now. Get personalized testThe automated classification of these embryo images will have the advantage of reducing time and costs,.