Polycystic Ovarian Syndrome (PCOS) is a complicated menstrual sickness that affects a wide range of women of procreative lifetime. Its miles connected with a combination of signs, including abnormal menstrual cycles, hormonal imbalances, and the presence of more than one cyst on the ovaries. The current methods for diagnosing PCOS involve a comprehensive evaluation that includes medical history assessment, physical examinations, and laboratory tests. However, these approaches have limitations. They can be time-consuming, relying on the subjective judgment and expertise of healthcare professionals. In light of these challenges, there is a growing need for more advanced and efficient methods of diagnosing PCOS. By utilizing machine learning algorithms and computer vision techniques, such a system can provide an objective and reliable approach to identify PCOS based on ultrasound images.