Abstract: A substrate treating method for removing a dielectric by-product produced by etching a dielectric film formed on a substrate, includes: providing a gaseous boron compound into a reaction chamber to remove the dielectric by-product; and purging an inside of the reaction chamber. The boron compound is represented by BnX3n, where X is hydrogen, alkyl, amino, or halogen, and n is a natural number greater than or equal to 1.

Abstract: There is provided a method of processing a substrate comprising an ONO stack in which a silicon oxide layer and a silicon nitride layer are stacked alternately and repeatedly on the substrate. The method includes: (a) primarily dry-etching silicon nitride layers of the ONO stack; (b) producing oxygen radicals and processing silicon oxide layers of the ONO stack with the oxygen radicals; and (c) secondarily dry-etching the silicon nitride layers of the ONO stack.

Abstract: The present invention relates to a substrate processing method for selectively etching a silicon nitride layer on a substrate on which silicon oxide layers and silicon nitride layers are alternately stacked, the method including plasma etching the silicon nitride layers using plasma of a plurality of gases, wherein the plurality of gases include a first gas containing fluorine excluding nitrogen trifluoride (NF3) and a second gas containing hydrogen, and the etch profile in the thickness direction of the silicon nitride layers is controlled by adjusting the atomic ratio of fluorine to hydrogen included in the plurality of gases.

Abstract: A method for recognizing an identification (ID) card of a user terminal using deep learning includes extracting an outline region of the ID card included in an input image using a first neural network model, modifying the ID card image of the image to a reference form using at least a partial value of the extracted outline region, and determining whether the modified ID card image is valid and recognizing text information in the valid ID card image. A recognition rate of the ID card may be increased by modifying an ID card image into a reference form using a trained neural network model.

Abstract: A method for recognizing an identification (ID) card of a user terminal using deep learning includes extracting an outline region of the ID card included in an input image using a first neural network model, modifying the ID card image of the image to a reference form using at least a partial value of the extracted outline region, and determining whether the modified ID card image is valid and recognizing text information in the valid ID card image. A recognition rate of the ID card may be increased by modifying an ID card image into a reference form using a trained neural network model.

Abstract: The invention provides novel substituted heterocyclic compounds represented by Formula I and Formula II, or a pharmaceutically acceptable salt, solvate, polymorph, ester, tautomer or prodrug thereof, and a composition comprising these compounds. The compounds provided can be used as inhibitors of MEK and are useful in the treatment of inflammatory diseases, cancer and other hyperproliferative diseases. The invention further provides a method of treatment for inflammatory diseases, cancer and other hyperproliferative diseases in mammals, especially humans.