> For the complete documentation index, see [llms.txt](https://docs.augelab.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.augelab.com/function-blocks/blocks-reference/image-transformations/analysis/non-zero-of-image.md).

# Non-zero of Image

This block returns the total number of non-zero pixels found in an image. It is useful for quick measurements such as foreground pixel count, occupancy checks, or verifying mask coverage.

## 📥 Inputs <a href="#inputs" id="inputs"></a>

`Image Any` Provide the image you want to analyze. The block accepts color or grayscale images.

## 📤 Outputs <a href="#outputs" id="outputs"></a>

`Count` Total number of non-zero pixels detected in the provided image.

## 🕹️ Controls <a href="#controls" id="controls"></a>

This block has no user-facing controls. It runs automatically when an image is provided.

## ✨ Features <a href="#features" id="features"></a>

* Fast single-value result useful for simple analytics and decision making.
* Accepts both color and grayscale images (color images are internally interpreted for pixel activity).
* Works well as a lightweight metric for masks, binary results, or foreground detection.

## ⚙️ Running mechanism <a href="#how-it-works" id="how-it-works"></a>

When the block is evaluated it examines the provided image and counts pixels that are non-zero (i.e., contain useful/foreground information). The result is returned as a single numeric value through the `Count` output.

## 📝 Usage <a href="#usage" id="usage"></a>

1. Connect an image-producing block to the `Image Any` input.
2. Read the numeric result from the `Count` output to drive logic, logging, or alarms.
3. Combine with other blocks for pre-processing, visualization, or decision-making.

## 💡 Tips and Tricks <a href="#tips-and-tricks" id="tips-and-tricks"></a>

* Prepare a clear binary mask before counting by using `Image Threshold` or `Image Adaptive Threshold` to reduce false positives from noise.
* Use `Image ROI` or `Image ROI Select` to limit the counting area to a region of interest (for localized measurements).
* Reduce noise with `Blur`, `Bilateral Filter` or `Denoising` before counting to avoid inflated results.
* Visualize what is being counted by sending the same image to `Show Image` or overlay results with `Draw Result On Image` / `Write Text On Image`.
* Log numeric results over time using `CSV Export` or `Data to JSON` for trend analysis or record keeping.
* Combine with `Logic Input` or comparison blocks to trigger actions when the count crosses a threshold.

## 🛠️ Troubleshooting <a href="#troubleshooting" id="troubleshooting"></a>

* Unexpectedly high counts: check for image noise or stray pixels. Apply `Image Threshold` and smoothing blocks to clean the input.
* Zero or very low counts: confirm the upstream image is valid using `Show Image` and ensure the area of interest contains the expected foreground.
* Counts vary unexpectedly between frames: restrict the area with `Image ROI` or stabilize the input using filters to reduce frame-to-frame variation.