An optical measurement system comprises a polarization beam splitter for dividing an incident beam into a reference beam and a measurement beam, a first beam splitter for reflecting the measurement beam to form a first reflected measurement beam, a spatial light modulator for modulating the first reflected measurement beam to form a modulated measurement beam, a condenser lens for focusing the modulated measurement beam to an object to form a penetrating measurement beam, an objective lens for converting the penetrating measurement beam into a parallel measurement beam, a mirror for reflecting the parallel measurement beam to form an object beam, a second beam splitter for reflecting the reference beam to a path coincident with that of the object beam, and a camera for receiving an interference signal generated by the reference beam and the object beam to generate an image of the object.

Embodiments of the present disclosure provide for improved generation and outputting of object identification data indicating object classifications for object representations. Such objects representations may correspond to depictions of objects in images captured using digital holographic microscopy. Some embodiments generate object identification data by comparing object representations in focused image(s) with specially configured annotated focused images, for example using a specially trained neural network or other machine learning model trained based on such annotated focused images. The annotated focused images are generated including a plurality of channels, each associated with a different grayscale focused image at a different target focal length of a range of target focal lengths. In this regard, model(s), algorithm(s), and/or other specially configured implementations may learn the spatial features of particular object representations and associated object identification data. The trained models may be used to perform accurate comparisons with the annotated focused images.

The present invention provides a surface shape measuring device and a surface shape measuring method which do not require a physical reference plane and can improve measurement accuracy without using a mechanical adjustment mechanism. The illumination light condensing point P.sub.Q and the reference light condensing point P.sub.L are arranged as mirror images of each other with respect to the virtual plane VP, and each data of the object light O, being a reflected light of the spherical wave illumination light Q, and the inline spherical wave reference light L is recorded on each hologram. On the virtual plane VP, the reconstructed object light hologram h.sup.V for measurement is generated, and the spherical wave optical hologram s.sup.V representing a spherical wave light emitted from the reference light condensing point P.sub.L is analytically generated. The height distribution of the surface to be measured of the object 4 is obtained from the phase distribution obtained by dividing the reconstructed object light hologram h.sup.V by the spherical wave light hologram s.sup.V. High-accuracy surface shape measurement without requiring a reference plane such as a glass substrate is realized by comparing the phase data of the reflected light acquired from the surface to be measured and the phase distribution on the plane cut surface of the spherical wave obtained analytically.

An optical method of characterizing an object comprises providing an object to be characterized, the object having at least one nanoscale feature; illuminating the object with coherent plane wave optical radiation having a wavelength larger than the nanoscale feature; capturing a diffraction intensity pattern of the radiation which is scattered by the object; supplying the diffraction intensity pattern to a neural network trained with a training set of diffraction intensity patterns corresponding to other objects with a same nanoscale feature as the object to be characterized, the neural network configured to recover information about the object from the diffraction intensity pattern; and making a characterization of the object based on the recovered information.

The illumination light condensing point P.sub.Q and the reference light condensing point P.sub.L are arranged as mirror images of each other with respect to the virtual plane VP, and each data of the object light O, being a reflected light of the spherical wave illumination light Q, and the inline spherical wave reference light L is recorded on each hologram. On the virtual plane VP, the reconstructed object light hologram h.sup.V for measurement is generated, and the spherical wave optical hologram s.sup.V representing a spherical wave light emitted from the reference light condensing point P.sub.L is analytically generated. The height distribution of the surface to be measured of the object 4 is obtained from the phase distribution obtained by dividing the reconstructed object light hologram h.sup.V by the spherical wave light hologram s.sup.V.

A method comprises obtaining input data comprising a hologram of a 3-dimensional (3D) particle field, a depth map of the 3D particle field, and a maximum phase projection of the 3D particle field. The method also comprises applying a U-net convolutional neural network (CNN) to the input data to generate output data. Encoder blocks have residual connections between a first layer and a second layer that skips over a convolution layer of the encoder block. Decoder blocks have residual connections between a first layer and a second layer that skips over a convolution layer of the decoder block. The output data includes a channel in which pixel intensity corresponds to relative depth of particles in the 3D particle field and an output image indicating locations of centroids of the particles in the 3D particle field.

An advance in high-resolution optical metrology has been achieved by the introduction of incoherent holographic imaging. FINCH, an example of incoherent holography, is shown to simplify the process, eliminating many steps in metrology and at the same time increasing throughput, resolution and accuracy of the method. A proposed technique requires only a single image capture with a non-moving camera rather than the capture of multiple stacks of images requiring many camera exposures and movement of the camera or sample in the conventional techniques.

Microscope (2) comprising a coherent light source (4) producing a coherent light beam (7), a light beam guide system (6) comprising a beam splitter (14) configured to split the coherent light beam (7) into a reference beam (7a) and a sample illumination beam (7b), a sample holder (18) configured to hold a sample (1) to be observed, a sample illumination device (28) configured to direct the sample illumination beam (7b) through the sample and into a microscope objective (37), a beam reuniter (16) configured to reunite the reference beam and sample illumination beam after passage of the sample illumination beam through the sample to be observed, and a light sensing system (8) configured to capture at least phase and intensity values of the coherent light beam downstream of the beam reuniter.

An optical method of characterizing an object comprises providing an object to be characterized, the object having at least one nanoscale feature; illuminating the object with coherent plane wave optical radiation having a wavelength larger than the nanoscale feature; capturing a diffraction intensity pattern of the radiation which is scattered by the object; supplying the diffraction intensity pattern to a neural network trained with a training set of diffraction intensity patterns corresponding to other objects with a same nanoscale feature as the object to be characterized, the neural network configured to recover information about the object from the diffraction intensity pattern; and making a characterization of the object based on the recovered information.

Disclosed is an apparatus of analyzing a depth of a holographic image according to the present disclosure, which includes an acquisition unit that acquires a hologram, a restoration unit that restores a three-dimensional holographic image by irradiating the hologram with a light source, an image sensing unit that senses a depth information image of the restored holographic image, and an analysis display unit that analyzes a depth quality of the holographic image, based on the sensed depth information image, and the image sensing unit uses a lensless type of photosensor.