Study on Metal Detection with an Electromagnetic Induction Probe Utilizing a Rotating Magnetic Field

The present paper describes an investigation conducted on metal detectors installed with a scanning probe.The authors applied a rotating magnetic field probe to metal detection.The rotating magnetic field probe is comprised of two vertically placed rectangular exciting coils and a circular detecting coil.The experimental results confirmed that the probe can detect metal objects and provide more information about their shape,direction,and electromagnetic characteristics than conventional metal detector probes.A two-dimensional signal display shows a low-resolution image of the metal object and the signal phase indicates the object’s direction and electromagnetic characteristics.The experimental results show that excellent reconstruction of the surface shapes of metal objects can be obtained for both magnetic and nonmagnetic metals under present conditions.There is also the potential for the approximate shape of a metal object to be estimated from the reconstructed image.

A restoration method using dual generate adversarial networks for Chinese ancient characters

Ancient books that record the history of different periods are precious for human civilization.But the protection of them is facing serious problems such as aging.It is significant to repair the damaged characters in ancient books and restore their original textures.The requirement of the restoration of the damaged character is keeping the stroke shape correct and the font style consistent.In order to solve these problems,this paper proposes a new restoration method based on generative adversarial networks.We use the shape restoration network to complete the stroke shape recovery and the font style recovery.The texture repair network is responsible for reconstructing texture details.In order to improve the accuracy of the generator in the shape restoration network,we use the adversarial feature loss(AFL),which can update the generator and discriminator synchronously to replace the traditional perceptual loss.Meanwhile,the font style loss is proposed to maintain the stylistic consistency for the whole character.Our model is evaluated on the datasets Yi and Qing,and shows that it outperforms current state-of-the-art techniques quantitatively and qualitatively.In particular,the Structural Similarity has increased by 8.0%and 6.7%respectively on the two datasets.

Correction of Scanned Book Images

Because of the spine, a book cannot be set flat on a flat bed scanner. As a result, the image suffers from shape distortion, variable brightness, and blurred characters. This paper describes a method based on book shape analysis to address these problems. The algorithm utilizes the relation between the distance from a line segment on the book to the flat bed and its projected length. The correction process uses edge extraction, iterative boundary point computations, linear image transformation, and histogram modification. Experimental results show that the shape distortion and brightness variance problems are perfectly resolved by the method.