Fruit Recognition Dataset

The database used in this study is comprising of 44406 fruit images, which we collected in a period of 6 months. The images where made with in our lab’s environment under different scenarios which we mention below. We captured all the images on a clear background with resolution of 320×258 pixels. We used HD Logitech web camera to took the pictures. During collecting this database, we created all kind of challenges, which, we have to face in real-world recognition scenarios in supermarket and fruit shops such as light, shadow, sunshine, pose variation, to make our model robust for, it might be necessary to cope with illumination variation, camera capturing artifacts, specular reflection shading and shadows. We tested our model’s robustness in all scenarios and it perform quit well.本研究使用的数据库包含44406张水果图像，采集工作耗时6个月完成。所有图像均采集于本实验室环境下的多种场景，具体场景如下文所述。图像拍摄采用纯色背景，分辨率为320×258像素，采集设备为罗技（Logitech）高清网络摄像头。在构建该数据库的过程中，我们模拟了实体超市与水果店中水果识别场景下需面对的各类真实挑战，包括光照变化、阴影、自然光、拍摄姿态变化等，以确保所训练模型能够应对光照波动、摄像头采集伪影、镜面反射阴影等实际问题，具备更强的鲁棒性。我们在所有场景下对模型的鲁棒性进行了测试，模型均表现优异。