Photo Editing Glossary
Key terms in photo editing, AI image processing, and digital photography — explained in plain language.
Object Removal
Object Removal
The process of erasing unwanted elements from a photograph while reconstructing the area behind them.
Inpainting
A technique that fills in missing or damaged regions of an image by synthesizing new pixel data from surrounding context.
Content-Aware Fill
An editing feature that automatically fills a selected area with content that matches the surrounding image.
Clone Stamp
A manual editing tool that copies pixels from one area of an image and paints them onto another area.
Healing Brush
A retouching tool that blends sampled pixels with the target area, matching texture and lighting automatically.
Masking
A non-destructive technique that hides or reveals parts of an image layer without permanently deleting pixels.
Selection Tool
An editing tool that isolates a specific region of an image for targeted editing operations.
Feathering
A soft transition applied to the edge of a selection or mask, creating a gradual blend between selected and unselected areas.
Edge Detection
An algorithm that identifies boundaries between distinct regions in an image based on contrast, color, or texture changes.
Lasso Tool
A freehand selection tool that allows users to draw custom selection boundaries around objects or regions.
Background
Background Removal
The process of separating the main subject from its background and either deleting or replacing the background.
Transparent Background
An image background with no visible color, allowing the subject to be placed on any other background or surface.
Alpha Channel
An additional data channel in an image that stores transparency information for each pixel.
Chroma Key
A technique that removes a specific color (usually green or blue) from an image or video to replace it with a different background.
Background Replacement
The process of removing an existing background and substituting it with a new image, color, or generated scene.
Matte
A grayscale image that defines which parts of a photo are visible and which are hidden, used for compositing.
Cutout
An image of a subject that has been isolated from its background, typically saved with a transparent background.
Compositing
The process of combining visual elements from multiple sources into a single cohesive image.
Foreground Extraction
The process of identifying and isolating the primary subject from the background in an image.
Enhancement
Image Enhancement
The process of improving the visual quality of a photograph by adjusting sharpness, brightness, color, and detail.
Upscaling
Increasing the resolution of an image while adding meaningful detail rather than simply enlarging existing pixels.
Super Resolution
An AI technique that generates a high-resolution image from a low-resolution input by inferring missing detail.
Denoising
The process of reducing random visual noise (grain) from a photograph while preserving actual image detail.
Sharpening
An enhancement technique that increases edge contrast to make image details appear crisper and more defined.
Color Correction
The process of adjusting colors in an image to achieve accurate, natural-looking color reproduction.
White Balance
A color adjustment that ensures white objects appear truly white in a photo by compensating for the color temperature of the light source.
Exposure
The overall brightness of an image, determined by the amount of light that reached the camera sensor during capture.
Contrast
The range of brightness difference between the lightest and darkest areas of an image.
HDR
High Dynamic Range — a technique that captures or simulates a wider range of brightness levels than standard photography.
Dynamic Range
The ratio between the brightest and darkest areas that a camera sensor or display can capture or reproduce.
AI & Machine Learning
Generative Fill
An AI feature that creates new image content to fill selected areas, guided by the surrounding visual context.
Generative AI
Artificial intelligence systems that create new content — images, text, audio, or video — rather than simply analyzing existing data.
Diffusion Model
A type of generative AI that creates images by gradually removing noise from a random starting point, guided by learned patterns.
Neural Network
A computing system inspired by biological brain structures, consisting of interconnected nodes that process information in layers.
Deep Learning
A subset of machine learning that uses neural networks with many layers to learn complex patterns from large datasets.
Image Segmentation
The process of dividing an image into distinct regions, typically identifying and labeling different objects or areas.
Semantic Understanding
An AI system's ability to understand what objects and scenes are depicted in an image, not just their pixel patterns.
Text-to-Image
AI technology that generates images from written text descriptions (prompts).
Outpainting
An AI technique that extends an image beyond its original boundaries by generating new content that continues the existing scene.
Prompt Engineering
The practice of crafting precise text descriptions to guide AI image generation models toward desired visual outputs.
Image-to-Image
An AI generation technique that uses an existing image as a reference to guide the creation of a new image with modified characteristics.
ControlNet
A neural network architecture that adds spatial conditioning to diffusion models, enabling precise control over generated image structure.
Style Transfer
An AI technique that applies the artistic style of one image to the content of another, creating a new image that combines both.
Face Detection
An AI capability that locates and identifies human faces within images, enabling targeted portrait adjustments.
Depth Estimation
An AI technique that infers the three-dimensional distance of objects in a scene from a single two-dimensional photograph.
Prompt Weighting
A technique for emphasizing or de-emphasizing specific words in an AI image generation prompt to control their influence on the output.
Image Inpainting
The computational process of reconstructing missing or damaged regions of an image by synthesizing plausible content based on surrounding context.
Image Synthesis
The generation of entirely new images by AI models trained on large datasets, producing photorealistic or artistic visuals from noise, text, or other inputs.
Smart Cropping
AI-powered automatic cropping that identifies the most important region of an image and frames it optimally for a given aspect ratio.
General Photography
Resolution
The number of pixels in an image, typically expressed as width × height (e.g., 3000×2000 pixels).
DPI
Dots Per Inch — a measure of print resolution indicating how many ink dots fit in one linear inch of printed output.
Pixel
The smallest addressable element of a digital image, containing a single color value.
Aspect Ratio
The proportional relationship between an image's width and height, expressed as a ratio like 16:9 or 4:3.
Compression
The process of reducing image file size by encoding pixel data more efficiently, sometimes at the cost of quality.
Lossy vs Lossless
Two compression approaches: lossy permanently discards some data for smaller files; lossless preserves all original data.
RAW Format
An unprocessed image format that preserves all data captured by the camera sensor without in-camera processing or compression.
Metadata
Information stored within an image file that describes the image properties, capture settings, and context.
EXIF Data
Exchangeable Image File Format — a metadata standard that stores camera settings, date, location, and technical details within image files.
Color Space
A defined range of colors that an image can represent, determining the gamut of available colors.
Bit Depth
The number of bits used to represent each color channel per pixel, determining the total number of possible color values.
Histogram
A graph showing the distribution of brightness values in an image, from shadows (left) to highlights (right).