Lenses are used to form images of objects. They follow a parabolic profile, as dictated by the physics of imaging optics. The clarity of images is essential for object recognition. However, challenging image conditions limit the capability of forming clear images. This happens when objects are very small or far away. Such images make it difficult to apply neural networks for object recognition. Here, we overcome this challenge by replacing the parabolic lens with a trainable lens, which lets us extend the learning process from the digital into the physical world. The lens profile is parameterized by over 10 000 trainable parameters. When used for recognizing small objects with low resolution, the profile adapts to maximize the accuracy of the recognition. The resulting profile could be significantly different from a typical parabolic lens. We show that the object recognition accuracy is improved by more than 25% when the objects are 16 times smaller than their original size. Besides, incorporating the trainable lens before digital computing adds minimal computational time. Our method has potential application in biology, such as cell detection, in the semiconductor industry, such as detecting defects, and in salvage.

中文翻译：

---

使用可训练镜头识别小物体

透镜用于形成物体的图像。它们遵循抛物线轮廓，这是成像光学物理所规定的。图像的清晰度对于物体识别至关重要。然而，具有挑战性的图像条件限制了形成清晰图像的能力。当物体很小或很远时，就会发生这种情况。这样的图像使得将神经网络应用于物体识别变得困难。在这里，我们通过用可训练的镜头替换抛物线镜头来克服这一挑战，这让我们将学习过程从数字世界扩展到物理世界。镜头轮廓由超过 10 000 个可训练参数进行参数化。当用于识别低分辨率的小物体时，配置文件会进行调整以最大限度地提高识别的准确性。由此产生的轮廓可能与典型的抛物面透镜有很大不同。我们表明，当对象比原始大小小 16 倍时，对象识别精度提高了 25% 以上。此外，在数字计算之前结合可训练镜头增加了最少的计算时间。我们的方法在生物学（如细胞检测）、半导体行业（如检测缺陷）和抢救中具有潜在应用。