An image processing apparatus that eliminates a complicated operation when a document image is input. The apparatus has an image input device for inputting a document image. A detection device detects displacement of the document image input by the input device. A determination device determines the input conditions of the image input device when the displacement detected by the detection device is not greater than a predetermined value. A control device controls the input device based on the input conditions determined by the determination device so as to cause the input device to input the document image.