People of reproductive age, primarily women, often experience the endocrine condition known as polycystic ovary syndrome (PCOS). This complex illness is characterized by various clinical symptoms, including irregular menstrual periods, hyperandrogenism, and polycystic ovarian morphology. PCOS is associated with a range of metabolic and cardiovascular issues that significantly impact the overall health and well-being of affected individuals. Early diagnosis and treatment are crucial to mitigate these risks and enhance the quality of life for PCOS patients. This article explores the classification of images using both Deep CNN and Deep CNN with SVM layer. The extensive dataset comprises 7,805 samples, divided into training (5,464 samples), testing (780 samples), and validation (1,562 samples) sets. These samples are categorized for the binary classification which gives out the result as Consists of PCOS and does not consist of PCOS, and the results are remarkable, showcasing the potential of this deep learning system for early PCOS identification, achieving an accuracy of 99.89% and a loss of 0.0101.